Header logo is ps


2020


Grasping Field: Learning Implicit Representations for Human Grasps
Grasping Field: Learning Implicit Representations for Human Grasps

Karunratanakul, K., Yang, J., Zhang, Y., Black, M., Muandet, K., Tang, S.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract
Robotic grasping of house-hold objects has made remarkable progress in recent years. Yet, human grasps are still difficult to synthesize realistically. There are several key reasons: (1) the human hand has many degrees of freedom (more than robotic manipulators); (2) the synthesized hand should conform to the surface of the object; and (3) it should interact with the object in a semantically and physically plausible manner. To make progress in this direction, we draw inspiration from the recent progress on learning-based implicit representations for 3D object reconstruction. Specifically, we propose an expressive representation for human grasp modelling that is efficient and easy to integrate with deep neural networks. Our insight is that every point in a three-dimensional space can be characterized by the signed distances to the surface of the hand and the object, respectively. Consequently, the hand, the object, and the contact area can be represented by implicit surfaces in a common space, in which the proximity between the hand and the object can be modelled explicitly. We name this 3D to 2D mapping as Grasping Field, parameterize it with a deep neural network, and learn it from data. We demonstrate that the proposed grasping field is an effective and expressive representation for human grasp generation. Specifically, our generative model is able to synthesize high-quality human grasps, given only on a 3D object point cloud. The extensive experiments demonstrate that our generative model compares favorably with a strong baseline and approaches the level of natural human grasps. Furthermore, based on the grasping field representation, we propose a deep network for the challenging task of 3D hand-object interaction reconstruction from a single RGB image. Our method improves the physical plausibility of the hand-object contact reconstruction and achieves comparable performance for 3D hand reconstruction compared to state-of-the-art methods. Our model and code are available for research purpose at https://github.com/korrawe/grasping_field.

pdf arXiv code [BibTex]


{GIF}: Generative Interpretable Faces
GIF: Generative Interpretable Faces

Ghosh, P., Gupta, P. S., Uziel, R., Ranjan, A., Black, M. J., Bolkart, T.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract
Photo-realistic visualization and animation of expressive human faces have been a long standing challenge. 3D face modeling methods provide parametric control but generates unrealistic images, on the other hand, generative 2D models like GANs (Generative Adversarial Networks) output photo-realistic face images, but lack explicit control. Recent methods gain partial control, either by attempting to disentangle different factors in an unsupervised manner, or by adding control post hoc to a pre-trained model. Unconditional GANs, however, may entangle factors that are hard to undo later. We condition our generative model on pre-defined control parameters to encourage disentanglement in the generation process. Specifically, we condition StyleGAN2 on FLAME, a generative 3D face model. While conditioning on FLAME parameters yields unsatisfactory results, we find that conditioning on rendered FLAME geometry and photometric details works well. This gives us a generative 2D face model named GIF (Generative Interpretable Faces) that offers FLAME's parametric control. Here, interpretable refers to the semantic meaning of different parameters. Given FLAME parameters for shape, pose, expressions, parameters for appearance, lighting, and an additional style vector, GIF outputs photo-realistic face images. We perform an AMT based perceptual study to quantitatively and qualitatively evaluate how well GIF follows its conditioning. The code, data, and trained model are publicly available for research purposes at http://gif.is.tue.mpg.de

pdf project code [BibTex]

pdf project code [BibTex]


{PLACE}: Proximity Learning of Articulation and Contact in {3D} Environments
PLACE: Proximity Learning of Articulation and Contact in 3D Environments

Zhang, S., Zhang, Y., Ma, Q., Black, M. J., Tang, S.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract
High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps to represent the scene, and parametric human models to represent 3D bodies. While being straight-forward, their generated human-scene interactions often lack of naturalness and physical plausibility. Our key observation is that humans interact with the world through body-scene contact. To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world. To that end, we propose a novel interaction generation method, named PLACE(Proximity Learning of Articulation and Contact in 3D Environments), which explicitly models the proximity between the human body and the 3D scene around it. Specifically, given a set of basis points on a scene mesh, we leverage a conditional variational autoencoder to synthesize the minimum distances from the basis points to the human body surface. The generated proximal relationship exhibits which region of the scene is in contact with the person. Furthermore, based on such synthesized proximity, we are able to effectively obtain expressive 3D human bodies that interact with the 3D scene naturally. Our perceptual study shows that PLACE significantly improves the state-of-the-art method, approaching the realism of real human-scene interaction. We believe our method makes an important step towards the fully automatic synthesis of realistic 3D human bodies in 3D scenes. The code and model are available for research at https://sanweiliti.github.io/PLACE/PLACE.html

pdf arXiv project code [BibTex]

pdf arXiv project code [BibTex]


Learning a statistical full spine model from partial observations
Learning a statistical full spine model from partial observations

Meng, D., Keller, M., Boyer, E., Black, M., Pujades, S.

In Shape in Medical Imaging, pages: 122,133, (Editors: Reuter, Martin and Wachinger, Christian and Lombaert, Hervé and Paniagua, Beatriz and Goksel, Orcun and Rekik, Islem), Springer International Publishing, October 2020 (inproceedings)

Abstract
The study of the morphology of the human spine has attracted research attention for its many potential applications, such as image segmentation, bio-mechanics or pathology detection. However, as of today there is no publicly available statistical model of the 3D surface of the full spine. This is mainly due to the lack of openly available 3D data where the full spine is imaged and segmented. In this paper we propose to learn a statistical surface model of the full-spine (7 cervical, 12 thoracic and 5 lumbar vertebrae) from partial and incomplete views of the spine. In order to deal with the partial observations we use probabilistic principal component analysis (PPCA) to learn a surface shape model of the full spine. Quantitative evaluation demonstrates that the obtained model faithfully captures the shape of the population in a low dimensional space and generalizes to left out data. Furthermore, we show that the model faithfully captures the global correlations among the vertebrae shape. Given a partial observation of the spine, i.e. a few vertebrae, the model can predict the shape of unseen vertebrae with a mean error under 3 mm. The full-spine statistical model is trained on the VerSe 2019 public dataset and is publicly made available to the community for non-commercial purposes. (https://gitlab.inria.fr/spine/spine_model)

Gitlab Code PDF DOI [BibTex]

Gitlab Code PDF DOI [BibTex]


STAR: Sparse Trained Articulated Human Body Regressor
STAR: Sparse Trained Articulated Human Body Regressor

Osman, A. A. A., Bolkart, T., Black, M. J.

In European Conference on Computer Vision (ECCV) , August 2020 (inproceedings)

Abstract
The SMPL body model is widely used for the estimation, synthesis, and analysis of 3D human pose and shape. While popular, we show that SMPL has several limitations and introduce STAR, which is quantitatively and qualitatively superior to SMPL. First, SMPL has a huge number of parameters resulting from its use of global blend shapes. These dense pose-corrective offsets relate every vertex on the mesh to all the joints in the kinematic tree, capturing spurious long-range correlations. To address this, we define per-joint pose correctives and learn the subset of mesh vertices that are influenced by each joint movement. This sparse formulation results in more realistic deformations and significantly reduces the number of model parameters to 20% of SMPL. When trained on the same data as SMPL, STAR generalizes better despite having many fewer parameters. Second, SMPL factors pose-dependent deformations from body shape while, in reality, people with different shapes deform differently. Consequently, we learn shape-dependent pose-corrective blend shapes that depend on both body pose and BMI. Third, we show that the shape space of SMPL is not rich enough to capture the variation in the human population. We address this by training STAR with an additional 10,000 scans of male and female subjects, and show that this results in better model generalization. STAR is compact, generalizes better to new bodies and is a drop-in replacement for SMPL. STAR is publicly available for research purposes at http://star.is.tue.mpg.de.

Project Page Code Video paper supplemental [BibTex]


Monocular Expressive Body Regression through Body-Driven Attention
Monocular Expressive Body Regression through Body-Driven Attention

Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M. J.

In Computer Vision – ECCV 2020, Springer International Publishing, Cham, August 2020 (inproceedings)

Abstract
To understand how people look, interact, or perform tasks,we need to quickly and accurately capture their 3D body, face, and hands together from an RGB image. Most existing methods focus only on parts of the body. A few recent approaches reconstruct full expressive 3D humans from images using 3D body models that include the face and hands. These methods are optimization-based and thus slow, prone to local optima, and require 2D keypoints as input. We address these limitations by introducing ExPose (EXpressive POse and Shape rEgression), which directly regresses the body, face, and hands, in SMPL-X format, from an RGB image. This is a hard problem due to the high dimensionality of the body and the lack of expressive training data. Additionally, hands and faces are much smaller than the body, occupying very few image pixels. This makes hand and face estimation hard when body images are downscaled for neural networks. We make three main contributions. First, we account for the lack of training data by curating a dataset of SMPL-X fits on in-the-wild images. Second, we observe that body estimation localizes the face and hands reasonably well. We introduce body-driven attention for face and hand regions in the original image to extract higher-resolution crops that are fed to dedicated refinement modules. Third, these modules exploit part-specific knowledge from existing face and hand-only datasets. ExPose estimates expressive 3D humans more accurately than existing optimization methods at a small fraction of the computational cost. Our data, model and code are available for research at https://expose.is.tue.mpg.de.

code Short video Long video arxiv pdf suppl link (url) Project Page [BibTex]


GRAB: A Dataset of Whole-Body Human Grasping of Objects
GRAB: A Dataset of Whole-Body Human Grasping of Objects

Taheri, O., Ghorbani, N., Black, M. J., Tzionas, D.

In Computer Vision – ECCV 2020, Springer International Publishing, Cham, August 2020 (inproceedings)

Abstract
Training computers to understand, model, and synthesize human grasping requires a rich dataset containing complex 3D object shapes, detailed contact information, hand pose and shape, and the 3D body motion over time. While "grasping" is commonly thought of as a single hand stably lifting an object, we capture the motion of the entire body and adopt the generalized notion of "whole-body grasps". Thus, we collect a new dataset, called GRAB (GRasping Actions with Bodies), of whole-body grasps, containing full 3D shape and pose sequences of 10 subjects interacting with 51 everyday objects of varying shape and size. Given MoCap markers, we fit the full 3D body shape and pose, including the articulated face and hands, as well as the 3D object pose. This gives detailed 3D meshes over time, from which we compute contact between the body and object. This is a unique dataset, that goes well beyond existing ones for modeling and understanding how humans grasp and manipulate objects, how their full body is involved, and how interaction varies with the task. We illustrate the practical value of GRAB with an example application; we train GrabNet, a conditional generative network, to predict 3D hand grasps for unseen 3D object shapes. The dataset and code are available for research purposes at https://grab.is.tue.mpg.de.

pdf suppl video (long) video (short) link (url) DOI [BibTex]

pdf suppl video (long) video (short) link (url) DOI [BibTex]


Learning to Dress 3D People in Generative Clothing
Learning to Dress 3D People in Generative Clothing

Ma, Q., Yang, J., Ranjan, A., Pujades, S., Pons-Moll, G., Tang, S., Black, M. J.

In Computer Vision and Pattern Recognition (CVPR), pages: 6468-6477, IEEE, June 2020 (inproceedings)

Abstract
Three-dimensional human body models are widely used in the analysis of human pose and motion. Existing models, however, are learned from minimally-clothed 3D scans and thus do not generalize to the complexity of dressed people in common images and videos. Additionally, current models lack the expressive power needed to represent the complex non-linear geometry of pose-dependent clothing shape. To address this, we learn a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing. Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term on SMPL. Our model is conditioned on both pose and clothing type, giving the ability to draw samples of clothing to dress different body shapes in a variety of styles and poses. To preserve wrinkle detail, our Mesh-VAE-GAN extends patchwise discriminators to 3D meshes. Our model, named CAPE, represents global shape and fine local structure, effectively extending the SMPL body model to clothing. To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.

Project page Code Short video Long video arXiv DOI [BibTex]

Project page Code Short video Long video arXiv DOI [BibTex]


{GENTEL : GENerating Training data Efficiently for Learning to segment medical images}
GENTEL : GENerating Training data Efficiently for Learning to segment medical images

Thakur, R. P., Rocamora, S. P., Goel, L., Pohmann, R., Machann, J., Black, M. J.

Congrès Reconnaissance des Formes, Image, Apprentissage et Perception (RFAIP), June 2020 (conference)

Abstract
Accurately segmenting MRI images is crucial for many clinical applications. However, manually segmenting images with accurate pixel precision is a tedious and time consuming task. In this paper we present a simple, yet effective method to improve the efficiency of the image segmentation process. We propose to transform the image annotation task into a binary choice task. We start by using classical image processing algorithms with different parameter values to generate multiple, different segmentation masks for each input MRI image. Then, instead of segmenting the pixels of the images, the user only needs to decide whether a segmentation is acceptable or not. This method allows us to efficiently obtain high quality segmentations with minor human intervention. With the selected segmentations, we train a state-of-the-art neural network model. For the evaluation, we use a second MRI dataset (1.5T Dataset), acquired with a different protocol and containing annotations. We show that the trained network i) is able to automatically segment cases where none of the classical methods obtain a high quality result ; ii) generalizes to the second MRI dataset, which was acquired with a different protocol and was never seen at training time ; and iii) enables detection of miss-annotations in this second dataset. Quantitatively, the trained network obtains very good results: DICE score - mean 0.98, median 0.99- and Hausdorff distance (in pixels) - mean 4.7, median 2.0-.

Project Page PDF [BibTex]

Project Page PDF [BibTex]


Generating 3D People in Scenes without People
Generating 3D People in Scenes without People

Zhang, Y., Hassan, M., Neumann, H., Black, M. J., Tang, S.

In Computer Vision and Pattern Recognition (CVPR), pages: 6194-6204, June 2020 (inproceedings)

Abstract
We present a fully automatic system that takes a 3D scene and generates plausible 3D human bodies that are posed naturally in that 3D scene. Given a 3D scene without people, humans can easily imagine how people could interact with the scene and the objects in it. However, this is a challenging task for a computer as solving it requires that (1) the generated human bodies to be semantically plausible within the 3D environment (e.g. people sitting on the sofa or cooking near the stove), and (2) the generated human-scene interaction to be physically feasible such that the human body and scene do not interpenetrate while, at the same time, body-scene contact supports physical interactions. To that end, we make use of the surface-based 3D human model SMPL-X. We first train a conditional variational autoencoder to predict semantically plausible 3D human poses conditioned on latent scene representations, then we further refine the generated 3D bodies using scene constraints to enforce feasible physical interaction. We show that our approach is able to synthesize realistic and expressive 3D human bodies that naturally interact with 3D environment. We perform extensive experiments demonstrating that our generative framework compares favorably with existing methods, both qualitatively and quantitatively. We believe that our scene-conditioned 3D human generation pipeline will be useful for numerous applications; e.g. to generate training data for human pose estimation, in video games and in VR/AR. Our project page for data and code can be seen at: \url{https://vlg.inf.ethz.ch/projects/PSI/}.

Code PDF DOI [BibTex]

Code PDF DOI [BibTex]


Learning Physics-guided Face Relighting under Directional Light
Learning Physics-guided Face Relighting under Directional Light

Nestmeyer, T., Lalonde, J., Matthews, I., Lehrmann, A. M.

In Conference on Computer Vision and Pattern Recognition, pages: 5123-5132, IEEE/CVF, June 2020 (inproceedings) Accepted

Abstract
Relighting is an essential step in realistically transferring objects from a captured image into another environment. For example, authentic telepresence in Augmented Reality requires faces to be displayed and relit consistent with the observer's scene lighting. We investigate end-to-end deep learning architectures that both de-light and relight an image of a human face. Our model decomposes the input image into intrinsic components according to a diffuse physics-based image formation model. We enable non-diffuse effects including cast shadows and specular highlights by predicting a residual correction to the diffuse render. To train and evaluate our model, we collected a portrait database of 21 subjects with various expressions and poses. Each sample is captured in a controlled light stage setup with 32 individual light sources. Our method creates precise and believable relighting results and generalizes to complex illumination conditions and challenging poses, including when the subject is not looking straight at the camera.

Paper [BibTex]

Paper [BibTex]


{VIBE}: Video Inference for Human Body Pose and Shape Estimation
VIBE: Video Inference for Human Body Pose and Shape Estimation

Kocabas, M., Athanasiou, N., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 5252-5262, IEEE, June 2020 (inproceedings)

Abstract
Human motion is fundamental to understanding behavior. Despite progress on single-image 3D pose and shape estimation, existing video-based state-of-the-art methodsfail to produce accurate and natural motion sequences due to a lack of ground-truth 3D motion data for training. To address this problem, we propose “Video Inference for Body Pose and Shape Estimation” (VIBE), which makes use of an existing large-scale motion capture dataset (AMASS) together with unpaired, in-the-wild, 2D keypoint annotations. Our key novelty is an adversarial learning framework that leverages AMASS to discriminate between real human motions and those produced by our temporal pose and shape regression networks. We define a temporal network architecture and show that adversarial training, at the sequence level, produces kinematically plausible motion sequences without in-the-wild ground-truth 3D labels. We perform extensive experimentation to analyze the importance of motion and demonstrate the effectiveness of VIBE on challenging 3D pose estimation datasets, achieving state-of-the-art performance. Code and pretrained models are available at https://github.com/mkocabas/VIBE

arXiv code video supplemental video DOI Project Page [BibTex]

arXiv code video supplemental video DOI Project Page [BibTex]


From Variational to Deterministic Autoencoders
From Variational to Deterministic Autoencoders

Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B.

8th International Conference on Learning Representations (ICLR) , April 2020, *equal contribution (conference)

Abstract
Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce “blurry” images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

arXiv link (url) [BibTex]

arXiv link (url) [BibTex]


Attractiveness and Confidence in Walking Style of Male and Female Virtual Characters
Attractiveness and Confidence in Walking Style of Male and Female Virtual Characters

Thaler, A., Bieg, A., Mahmood, N., Black, M. J., Mohler, B. J., Troje, N. F.

In IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pages: 678-679, March 2020 (inproceedings)

Abstract
Animated virtual characters are essential to many applications. Little is known so far about biological and personality inferences made from a virtual character’s body shape and motion. Here, we investigated how sex-specific differences in walking style relate to the perceived attractiveness and confidence of male and female virtual characters. The characters were generated by reconstructing body shape and walking motion from optical motion capture data. The results suggest that sexual dimorphism in walking style plays a different role in attributing biological and personality traits to male and female virtual characters. This finding has important implications for virtual character animation.

pdf DOI [BibTex]

pdf DOI [BibTex]


Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations
Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations

Rueegg, N., Lassner, C., Black, M. J., Schindler, K.

In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), pages: 5561-5569, Febuary 2020 (inproceedings)

Abstract
The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision is available, but in problems like human pose and shape estimation, it is difficult to obtain natural images with 3D ground truth. To go one step further, we propose a new architecture that facilitates unsupervised, or lightly supervised, learning. The idea is to break the problem into a series of transformations between increasingly abstract representations. Each step involves a cycle designed to be learnable without annotated training data, and the chain of cycles delivers the final solution. Specifically, we use 2D body part segments as an intermediate representation that contains enough information to be lifted to 3D, and at the same time is simple enough to be learned in an unsupervised way. We demonstrate the method by learning 3D human pose and shape from un-paired and un-annotated images. We also explore varying amounts of paired data and show that cycling greatly alleviates the need for paired data. While we present results for modeling humans, our formulation is general and can be applied to other vision problems.

pdf [BibTex]

pdf [BibTex]

2016


Keep it {SMPL}: Automatic Estimation of {3D} Human Pose and Shape from a Single Image
Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image

Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M. J.

In Computer Vision – ECCV 2016, pages: 561-578, Lecture Notes in Computer Science, Springer International Publishing, October 2016 (inproceedings)

Abstract
We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of information about body shape. The problem is challenging because of the complexity of the human body, articulation, occlusion, clothing, lighting, and the inherent ambiguity in inferring 3D from 2D. To solve this, we fi rst use a recently published CNN-based method, DeepCut, to predict (bottom-up) the 2D body joint locations. We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints. We do so by minimizing an objective function that penalizes the error between the projected 3D model joints and detected 2D joints. Because SMPL captures correlations in human shape across the population, we are able to robustly fi t it to very little data. We further leverage the 3D model to prevent solutions that cause interpenetration. We evaluate our method, SMPLify, on the Leeds Sports, HumanEva, and Human3.6M datasets, showing superior pose accuracy with respect to the state of the art.

pdf Video Sup Mat video Code Project ppt Project Page [BibTex]

2016

pdf Video Sup Mat video Code Project ppt Project Page [BibTex]


Superpixel Convolutional Networks using Bilateral Inceptions
Superpixel Convolutional Networks using Bilateral Inceptions

Gadde, R., Jampani, V., Kiefel, M., Kappler, D., Gehler, P.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, Springer, October 2016 (inproceedings)

Abstract
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new “bilateral inception” module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respecting image edges, thus using the structured information of the problem for improved results. Second, the layer recovers a full resolution segmentation result from the lower resolution solution of a CNN. In the experiments, we modify several existing CNN architectures by inserting our inception modules between the last CNN (1 × 1 convolution) layers. Empirical results on three different datasets show reliable improvements not only in comparison to the baseline networks, but also in comparison to several dense-pixel prediction techniques such as CRFs, while being competitive in time.

pdf supplementary poster Project Page Project Page [BibTex]

pdf supplementary poster Project Page Project Page [BibTex]


Barrista - Caffe Well-Served
Barrista - Caffe Well-Served

Lassner, C., Kappler, D., Kiefel, M., Gehler, P.

In ACM Multimedia Open Source Software Competition, October 2016 (inproceedings)

Abstract
The caffe framework is one of the leading deep learning toolboxes in the machine learning and computer vision community. While it offers efficiency and configurability, it falls short of a full interface to Python. With increasingly involved procedures for training deep networks and reaching depths of hundreds of layers, creating configuration files and keeping them consistent becomes an error prone process. We introduce the barrista framework, offering full, pythonic control over caffe. It separates responsibilities and offers code to solve frequently occurring tasks for pre-processing, training and model inspection. It is compatible to all caffe versions since mid 2015 and can import and export .prototxt files. Examples are included, e.g., a deep residual network implemented in only 172 lines (for arbitrary depths), comparing to 2320 lines in the official implementation for the equivalent model.

pdf link (url) DOI Project Page [BibTex]

pdf link (url) DOI Project Page [BibTex]


Dynamic baseline stereo vision-based cooperative target tracking
Dynamic baseline stereo vision-based cooperative target tracking

Ahmad, A., Ruff, E., Bülthoff, H.

19th International Conference on Information Fusion, pages: 1728-1734, July 2016 (conference)

Abstract
In this article we present a new method for multi-robot cooperative target tracking based on dynamic baseline stereo vision. The core novelty of our approach includes a computationally light-weight scheme to compute the 3D stereo measurements that exactly satisfy the epipolar constraints and a covariance intersection (CI)-based method to fuse the 3D measurements obtained by each individual robot. Using CI we are able to systematically integrate the robot localization uncertainties as well as the uncertainties in the measurements generated by the monocular camera images from each individual robot into the resulting stereo measurements. Through an extensive set of simulation and real robot results we show the robustness and accuracy of our approach with respect to ground truth. The source code related to this article is publicly accessible on our website and the datasets are available on request.

DOI [BibTex]

DOI [BibTex]


DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B.

In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 4929-4937, IEEE, June 2016 (inproceedings)

Abstract
This paper considers the task of articulated human pose estimation of multiple people in real-world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other. This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation.

code pdf supplementary DOI Project Page [BibTex]

code pdf supplementary DOI Project Page [BibTex]


Video segmentation via object flow
Video segmentation via object flow

Tsai, Y., Yang, M., Black, M. J.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
Video object segmentation is challenging due to fast moving objects, deforming shapes, and cluttered backgrounds. Optical flow can be used to propagate an object segmentation over time but, unfortunately, flow is often inaccurate, particularly around object boundaries. Such boundaries are precisely where we want our segmentation to be accurate. To obtain accurate segmentation across time, we propose an efficient algorithm that considers video segmentation and optical flow estimation simultaneously. For video segmentation, we formulate a principled, multiscale, spatio-temporal objective function that uses optical flow to propagate information between frames. For optical flow estimation, particularly at object boundaries, we compute the flow independently in the segmented regions and recompose the results. We call the process object flow and demonstrate the effectiveness of jointly optimizing optical flow and video segmentation using an iterative scheme. Experiments on the SegTrack v2 and Youtube-Objects datasets show that the proposed algorithm performs favorably against the other state-of-the-art methods.

pdf [BibTex]

pdf [BibTex]


Patches, Planes and Probabilities: A Non-local Prior for Volumetric {3D} Reconstruction
Patches, Planes and Probabilities: A Non-local Prior for Volumetric 3D Reconstruction

Ulusoy, A. O., Black, M. J., Geiger, A.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
In this paper, we propose a non-local structured prior for volumetric multi-view 3D reconstruction. Towards this goal, we present a novel Markov random field model based on ray potentials in which assumptions about large 3D surface patches such as planarity or Manhattan world constraints can be efficiently encoded as probabilistic priors. We further derive an inference algorithm that reasons jointly about voxels, pixels and image segments, and estimates marginal distributions of appearance, occupancy, depth, normals and planarity. Key to tractable inference is a novel hybrid representation that spans both voxel and pixel space and that integrates non-local information from 2D image segmentations in a principled way. We compare our non-local prior to commonly employed local smoothness assumptions and a variety of state-of-the-art volumetric reconstruction baselines on challenging outdoor scenes with textureless and reflective surfaces. Our experiments indicate that regularizing over larger distances has the potential to resolve ambiguities where local regularizers fail.

YouTube pdf poster suppmat Project Page [BibTex]


Optical Flow with Semantic Segmentation and Localized Layers
Optical Flow with Semantic Segmentation and Localized Layers

Sevilla-Lara, L., Sun, D., Jampani, V., Black, M. J.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 3889-3898, June 2016 (inproceedings)

Abstract
Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move differently. Here we exploit recent advances in static semantic scene segmentation to segment the image into objects of different types. We define different models of image motion in these regions depending on the type of object. For example, we model the motion on roads with homographies, vegetation with spatially smooth flow, and independently moving objects like cars and planes with affine motion plus deviations. We then pose the flow estimation problem using a novel formulation of localized layers, which addresses limitations of traditional layered models for dealing with complex scene motion. Our semantic flow method achieves the lowest error of any published monocular method in the KITTI-2015 flow benchmark and produces qualitatively better flow and segmentation than recent top methods on a wide range of natural videos.

video Kitti Precomputed Data (1.6GB) pdf YouTube Sequences Code Project Page Project Page [BibTex]


Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Jampani, V., Kiefel, M., Gehler, P. V.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 4452-4461, June 2016 (inproceedings)

Abstract
Bilateral filters have wide spread use due to their edge-preserving properties. The common use case is to manually choose a parametric filter type, usually a Gaussian filter. In this paper, we will generalize the parametrization and in particular derive a gradient descent algorithm so the filter parameters can be learned from data. This derivation allows to learn high dimensional linear filters that operate in sparsely populated feature spaces. We build on the permutohedral lattice construction for efficient filtering. The ability to learn more general forms of high-dimensional filters can be used in several diverse applications. First, we demonstrate the use in applications where single filter applications are desired for runtime reasons. Further, we show how this algorithm can be used to learn the pairwise potentials in densely connected conditional random fields and apply these to different image segmentation tasks. Finally, we introduce layers of bilateral filters in CNNs and propose bilateral neural networks for the use of high-dimensional sparse data. This view provides new ways to encode model structure into network architectures. A diverse set of experiments empirically validates the usage of general forms of filters.

project page code CVF open-access pdf supplementary poster Project Page Project Page [BibTex]


Occlusion boundary detection via deep exploration of context
Occlusion boundary detection via deep exploration of context

Fu, H., Wang, C., Tao, D., Black, M. J.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
Occlusion boundaries contain rich perceptual information about the underlying scene structure. They also provide important cues in many visual perception tasks such as scene understanding, object recognition, and segmentation. In this paper, we improve occlusion boundary detection via enhanced exploration of contextual information (e.g., local structural boundary patterns, observations from surrounding regions, and temporal context), and in doing so develop a novel approach based on convolutional neural networks (CNNs) and conditional random fields (CRFs). Experimental results demonstrate that our detector significantly outperforms the state-of-the-art (e.g., improving the F-measure from 0.62 to 0.71 on the commonly used CMU benchmark). Last but not least, we empirically assess the roles of several important components of the proposed detector, so as to validate the rationale behind this approach.

pdf [BibTex]

pdf [BibTex]


Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

Xie, J., Kiefel, M., Sun, M., Geiger, A.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)

Abstract
Semantic annotations are vital for training models for object recognition, semantic segmentation or scene understanding. Unfortunately, pixelwise annotation of images at very large scale is labor-intensive and only little labeled data is available, particularly at instance level and for street scenes. In this paper, we propose to tackle this problem by lifting the semantic instance labeling task from 2D into 3D. Given reconstructions from stereo or laser data, we annotate static 3D scene elements with rough bounding primitives and develop a probabilistic model which transfers this information into the image domain. We leverage our method to obtain 2D labels for a novel suburban video dataset which we have collected, resulting in 400k semantic and instance image annotations. A comparison of our method to state-of-the-art label transfer baselines reveals that 3D information enables more efficient annotation while at the same time resulting in improved accuracy and time-coherent labels.

pdf suppmat Project Page Project Page [BibTex]

pdf suppmat Project Page Project Page [BibTex]


Appealing female avatars from {3D} body scans: Perceptual effects of stylization
Appealing female avatars from 3D body scans: Perceptual effects of stylization

Fleming, R., Mohler, B., Romero, J., Black, M. J., Breidt, M.

In 11th Int. Conf. on Computer Graphics Theory and Applications (GRAPP), Febuary 2016 (inproceedings)

Abstract
Advances in 3D scanning technology allow us to create realistic virtual avatars from full body 3D scan data. However, negative reactions to some realistic computer generated humans suggest that this approach might not always provide the most appealing results. Using styles derived from existing popular character designs, we present a novel automatic stylization technique for body shape and colour information based on a statistical 3D model of human bodies. We investigate whether such stylized body shapes result in increased perceived appeal with two different experiments: One focuses on body shape alone, the other investigates the additional role of surface colour and lighting. Our results consistently show that the most appealing avatar is a partially stylized one. Importantly, avatars with high stylization or no stylization at all were rated to have the least appeal. The inclusion of colour information and improvements to render quality had no significant effect on the overall perceived appeal of the avatars, and we observe that the body shape primarily drives the change in appeal ratings. For body scans with colour information, we found that a partially stylized avatar was most effective, increasing average appeal ratings by approximately 34%.

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Deep Discrete Flow
Deep Discrete Flow

Güney, F., Geiger, A.

Asian Conference on Computer Vision (ACCV), 2016 (conference) Accepted

pdf suppmat Project Page [BibTex]

pdf suppmat Project Page [BibTex]


Multi-Person Tracking by Multicuts and Deep Matching
Multi-Person Tracking by Multicuts and Deep Matching

(Winner of the Multi-Object Tracking Challenge ECCV 2016)

Tang, S., Andres, B., Andriluka, M., Schiele, B.

ECCV Workshop on Benchmarking Mutliple Object Tracking, 2016 (conference)

PDF [BibTex]

PDF [BibTex]


Reconstructing Articulated Rigged Models from RGB-D Videos
Reconstructing Articulated Rigged Models from RGB-D Videos

Tzionas, D., Gall, J.

In European Conference on Computer Vision Workshops 2016 (ECCVW’16) - Workshop on Recovering 6D Object Pose (R6D’16), pages: 620-633, Springer International Publishing, 2016 (inproceedings)

Abstract
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consists of a watertight mesh, embedded skeleton, and skinning weights.

pdf suppl Project's Website YouTube link (url) DOI [BibTex]

pdf suppl Project's Website YouTube link (url) DOI [BibTex]


A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects
A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

Keuper, M., Tang, S., Yu, Z., Andres, B., Brox, T., Schiele, B.

In arXiv:1607.06317, 2016 (inproceedings)

PDF [BibTex]

PDF [BibTex]

2003


Image statistics and anisotropic diffusion
Image statistics and anisotropic diffusion

Scharr, H., Black, M. J., Haussecker, H.

In Int. Conf. on Computer Vision, pages: 840-847, October 2003 (inproceedings)

pdf [BibTex]

2003

pdf [BibTex]


A switching {Kalman} filter model for the motor cortical coding of hand motion
A switching Kalman filter model for the motor cortical coding of hand motion

Wu, W., Black, M. J., Mumford, D., Gao, Y., Bienenstock, E., Donoghue, J. P.

In Proc. IEEE Engineering in Medicine and Biology Society, pages: 2083-2086, September 2003 (inproceedings)

pdf [BibTex]

pdf [BibTex]


no image
A Gaussian mixture model for the motor cortical coding of hand motion

Wu, W., Mumford, D., Black, M. J., Gao, Y., Bienenstock, E., Donoghue, J. P.

Neural Control of Movement, Santa Barbara, CA, April 2003 (conference)

abstract [BibTex]

abstract [BibTex]


Connecting brains with machines: The neural control of {2D} cursor movement
Connecting brains with machines: The neural control of 2D cursor movement

Black, M. J., Bienenstock, E., Donoghue, J. P., Serruya, M., Wu, W., Gao, Y.

In 1st International IEEE/EMBS Conference on Neural Engineering, pages: 580-583, Capri, Italy, March 2003 (inproceedings)

pdf [BibTex]

pdf [BibTex]


A quantitative comparison of linear and non-linear models of motor cortical activity for the encoding and decoding of arm motions
A quantitative comparison of linear and non-linear models of motor cortical activity for the encoding and decoding of arm motions

Gao, Y., Black, M. J., Bienenstock, E., Wu, W., Donoghue, J. P.

In 1st International IEEE/EMBS Conference on Neural Engineering, pages: 189-192, Capri, Italy, March 2003 (inproceedings)

pdf [BibTex]

pdf [BibTex]


no image
Accuracy of manual spike sorting: Results for the Utah intracortical array

Wood, F., Fellows, M., Vargas-Irwin, C., Black, M. J., Donoghue, J. P.

Program No. 279.2. 2003, Abstract Viewer and Itinerary Planner, Society for Neuroscience, Washington, DC, 2003, Online (conference)

abstract [BibTex]

abstract [BibTex]


no image
Specular flow and the perception of surface reflectance

Roth, S., Domini, F., Black, M. J.

Journal of Vision, 3 (9): 413a, 2003 (conference)

abstract poster [BibTex]

abstract poster [BibTex]


Attractive people: Assembling loose-limbed models using non-parametric belief propagation
Attractive people: Assembling loose-limbed models using non-parametric belief propagation

Sigal, L., Isard, M. I., Sigelman, B. H., Black, M. J.

In Advances in Neural Information Processing Systems 16, NIPS, pages: 1539-1546, (Editors: S. Thrun and L. K. Saul and B. Schölkopf), MIT Press, 2003 (inproceedings)

Abstract
The detection and pose estimation of people in images and video is made challenging by the variability of human appearance, the complexity of natural scenes, and the high dimensionality of articulated body models. To cope with these problems we represent the 3D human body as a graphical model in which the relationships between the body parts are represented by conditional probability distributions. We formulate the pose estimation problem as one of probabilistic inference over a graphical model where the random variables correspond to the individual limb parameters (position and orientation). Because the limbs are described by 6-dimensional vectors encoding pose in 3-space, discretization is impractical and the random variables in our model must be continuous-valued. To approximate belief propagation in such a graph we exploit a recently introduced generalization of the particle filter. This framework facilitates the automatic initialization of the body-model from low level cues and is robust to occlusion of body parts and scene clutter.

pdf (color) pdf (black and white) [BibTex]

pdf (color) pdf (black and white) [BibTex]


Neural decoding of cursor motion using a {Kalman} filter
Neural decoding of cursor motion using a Kalman filter

(Nominated: Best student paper)

Wu, W., Black, M. J., Gao, Y., Bienenstock, E., Serruya, M., Shaikhouni, A., Donoghue, J. P.

In Advances in Neural Information Processing Systems 15, pages: 133-140, MIT Press, 2003 (inproceedings)

pdf [BibTex]

pdf [BibTex]

2002


Inferring hand motion from multi-cell recordings in motor cortex using a {Kalman} filter
Inferring hand motion from multi-cell recordings in motor cortex using a Kalman filter

Wu, W., Black, M. J., Gao, Y., Bienenstock, E., Serruya, M., Donoghue, J. P.

In SAB’02-Workshop on Motor Control in Humans and Robots: On the Interplay of Real Brains and Artificial Devices, pages: 66-73, Edinburgh, Scotland (UK), August 2002 (inproceedings)

pdf [BibTex]

2002

pdf [BibTex]


no image
Inferring hand motion from multi-cell recordings in motor cortex using a Kalman filter

Wu, W., Black M., Gao, Y., Bienenstock, E., Serruya, M., Donoghue, J.

Program No. 357.5. 2002 Abstract Viewer/Itinerary Planner, Society for Neuroscience, Washington, DC, 2002, Online (conference)

abstract [BibTex]

abstract [BibTex]


Probabilistic inference of hand motion from neural activity in motor cortex
Probabilistic inference of hand motion from neural activity in motor cortex

Gao, Y., Black, M. J., Bienenstock, E., Shoham, S., Donoghue, J.

In Advances in Neural Information Processing Systems 14, pages: 221-228, MIT Press, 2002 (inproceedings)

Abstract
Statistical learning and probabilistic inference techniques are used to infer the hand position of a subject from multi-electrode recordings of neural activity in motor cortex. First, an array of electrodes provides train- ing data of neural firing conditioned on hand kinematics. We learn a non- parametric representation of this firing activity using a Bayesian model and rigorously compare it with previous models using cross-validation. Second, we infer a posterior probability distribution over hand motion conditioned on a sequence of neural test data using Bayesian inference. The learned firing models of multiple cells are used to define a non- Gaussian likelihood term which is combined with a prior probability for the kinematics. A particle filtering method is used to represent, update, and propagate the posterior distribution over time. The approach is com- pared with traditional linear filtering methods; the results suggest that it may be appropriate for neural prosthetic applications.

pdf [BibTex]

pdf [BibTex]


Automatic detection and tracking of human motion with a view-based representation
Automatic detection and tracking of human motion with a view-based representation

Fablet, R., Black, M. J.

In European Conf. on Computer Vision, ECCV 2002, 1, pages: 476-491, LNCS 2353, (Editors: A. Heyden and G. Sparr and M. Nielsen and P. Johansen), Springer-Verlag , 2002 (inproceedings)

Abstract
This paper proposes a solution for the automatic detection and tracking of human motion in image sequences. Due to the complexity of the human body and its motion, automatic detection of 3D human motion remains an open, and important, problem. Existing approaches for automatic detection and tracking focus on 2D cues and typically exploit object appearance (color distribution, shape) or knowledge of a static background. In contrast, we exploit 2D optical flow information which provides rich descriptive cues, while being independent of object and background appearance. To represent the optical flow patterns of people from arbitrary viewpoints, we develop a novel representation of human motion using low-dimensional spatio-temporal models that are learned using motion capture data of human subjects. In addition to human motion (the foreground) we probabilistically model the motion of generic scenes (the background); these statistical models are defined as Gibbsian fields specified from the first-order derivatives of motion observations. Detection and tracking are posed in a principled Bayesian framework which involves the computation of a posterior probability distribution over the model parameters (i.e., the location and the type of the human motion) given a sequence of optical flow observations. Particle filtering is used to represent and predict this non-Gaussian posterior distribution over time. The model parameters of samples from this distribution are related to the pose parameters of a 3D articulated model (e.g. the approximate joint angles and movement direction). Thus the approach proves suitable for initializing more complex probabilistic models of human motion. As shown by experiments on real image sequences, our method is able to detect and track people under different viewpoints with complex backgrounds.

pdf [BibTex]

pdf [BibTex]


A layered motion representation with occlusion and compact spatial support
A layered motion representation with occlusion and compact spatial support

Fleet, D. J., Jepson, A., Black, M. J.

In European Conf. on Computer Vision, ECCV 2002, 1, pages: 692-706, LNCS 2353, (Editors: A. Heyden and G. Sparr and M. Nielsen and P. Johansen), Springer-Verlag , 2002 (inproceedings)

Abstract
We describe a 2.5D layered representation for visual motion analysis. The representation provides a global interpretation of image motion in terms of several spatially localized foreground regions along with a background region. Each of these regions comprises a parametric shape model and a parametric motion model. The representation also contains depth ordering so visibility and occlusion are rightly included in the estimation of the model parameters. Finally, because the number of objects, their positions, shapes and sizes, and their relative depths are all unknown, initial models are drawn from a proposal distribution, and then compared using a penalized likelihood criterion. This allows us to automatically initialize new models, and to compare different depth orderings.

pdf [BibTex]

pdf [BibTex]


Implicit probabilistic models of human motion for synthesis and tracking
Implicit probabilistic models of human motion for synthesis and tracking

Sidenbladh, H., Black, M. J., Sigal, L.

In European Conf. on Computer Vision, 1, pages: 784-800, 2002 (inproceedings)

Abstract
This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an explicit probabilistic model from available training data is currently impractical. Instead we exploit methods from texture synthesis that treat images as representing an implicit empirical distribution. These methods replace the problem of representing the probability of a texture pattern with that of searching the training data for similar instances of that pattern. We extend this idea to temporal data representing 3D human motion with a large database of example motions. To make the method useful in practice, we must address the problem of efficient search in a large training set; efficiency is particularly important for tracking. Towards that end, we learn a low dimensional linear model of human motion that is used to structure the example motion database into a binary tree. An approximate probabilistic tree search method exploits the coefficients of this low-dimensional representation and runs in sub-linear time. This probabilistic tree search returns a particular sample human motion with probability approximating the true distribution of human motions in the database. This sampling method is suitable for use with particle filtering techniques and is applied to articulated 3D tracking of humans within a Bayesian framework. Successful tracking results are presented, along with examples of synthesizing human motion using the model.

pdf [BibTex]

pdf [BibTex]


Robust parameterized component analysis: Theory and applications to {2D} facial modeling
Robust parameterized component analysis: Theory and applications to 2D facial modeling

De la Torre, F., Black, M. J.

In European Conf. on Computer Vision, ECCV 2002, 4, pages: 653-669, LNCS 2353, Springer-Verlag, 2002 (inproceedings)

pdf [BibTex]

pdf [BibTex]

2001


Dynamic coupled component analysis
Dynamic coupled component analysis

De la Torre, F., Black, M. J.

In IEEE Proc. Computer Vision and Pattern Recognition, CVPR’01, 2, pages: 643-650, IEEE, Kauai, Hawaii, December 2001 (inproceedings)

pdf [BibTex]

2001

pdf [BibTex]


Robust principal component analysis for computer vision
Robust principal component analysis for computer vision

De la Torre, F., Black, M. J.

In Int. Conf. on Computer Vision, ICCV-2001, II, pages: 362-369, Vancouver, BC, USA, 2001 (inproceedings)

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Learning image statistics for {Bayesian} tracking
Learning image statistics for Bayesian tracking

Sidenbladh, H., Black, M. J.

In Int. Conf. on Computer Vision, ICCV-2001, II, pages: 709-716, Vancouver, BC, USA, 2001 (inproceedings)

pdf [BibTex]

pdf [BibTex]