Header logo is ps


2020


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), 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.

arxiv project page [BibTex]

2020


{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-.

[BibTex]

[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), 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 [BibTex]

Code PDF [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, 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 Computer Vision and Pattern Recognition (CVPR), 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 [BibTex]

arXiv code [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) Accepted

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 [BibTex]

arXiv [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), 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]

1999


Edges as outliers: Anisotropic smoothing using local image statistics
Edges as outliers: Anisotropic smoothing using local image statistics

Black, M. J., Sapiro, G.

In Scale-Space Theories in Computer Vision, Second Int. Conf., Scale-Space ’99, pages: 259-270, LNCS 1682, Springer, Corfu, Greece, September 1999 (inproceedings)

Abstract
Edges are viewed as statistical outliers with respect to local image gradient magnitudes. Within local image regions we compute a robust statistical measure of the gradient variation and use this in an anisotropic diffusion framework to determine a spatially varying "edge-stopping" parameter σ. We show how to determine this parameter for two edge-stopping functions described in the literature (Perona-Malik and the Tukey biweight). Smoothing of the image is related the local texture and in regions of low texture, small gradient values may be treated as edges whereas in regions of high texture, large gradient magnitudes are necessary before an edge is preserved. Intuitively these results have similarities with human perceptual phenomena such as masking and "popout". Results are shown on a variety of standard images.

pdf [BibTex]

1999

pdf [BibTex]


Probabilistic detection and tracking of motion discontinuities
Probabilistic detection and tracking of motion discontinuities

(Marr Prize, Honorable Mention)

Black, M. J., Fleet, D. J.

In Int. Conf. on Computer Vision, ICCV-99, pages: 551-558, ICCV, Corfu, Greece, September 1999 (inproceedings)

pdf [BibTex]

pdf [BibTex]


Artscience Sciencart
Artscience Sciencart

Black, M. J., Levy, D., PamelaZ,

In Art and Innovation: The Xerox PARC Artist-in-Residence Program, pages: 244-300, (Editors: Harris, C.), MIT-Press, 1999 (incollection)

Abstract
One of the effects of the PARC Artist In Residence (PAIR) program has been to expose the strong connections between scientists and artists. Both do what they do because they need to do it. They are often called upon to justify their work in order to be allowed to continue to do it. They need to justify it to funders, to sponsoring institutions, corporations, the government, the public. They publish papers, teach workshops, and write grants touting the educational or health benefits of what they do. All of these things are to some extent valid, but the fact of the matter is: artists and scientists do their work because they are driven to do it. They need to explore and create.

This chapter attempts to give a flavor of one multi-way "PAIRing" between performance artist PamelaZ and two PARC researchers, Michael Black and David Levy. The three of us paired up because we found each other interesting. We chose each other. While most artists in the program are paired with a single researcher Pamela jokingly calls herself a bigamist for choosing two PAIR "husbands" with different backgrounds and interests.

There are no "rules" to the PAIR program; no one told us what to do with our time. Despite this we all had a sense that we needed to produce something tangible during Pamela's year-long residency. In fact, Pamela kept extending her residency because she did not feel as though we had actually made anything concrete. The interesting thing was that all along we were having great conversations, some of which Pamela recorded. What we did not see at the time was that it was these conversations between artists and scientists that are at the heart of the PAIR program and that these conversations were changing the way we thought about our own work and the relationships between science and art.

To give these conversations their due, and to allow the reader into our PAIR interactions, we include two of our many conversations in this chapter.

[BibTex]

[BibTex]


Explaining optical flow events with parameterized spatio-temporal models
Explaining optical flow events with parameterized spatio-temporal models

Black, M. J.

In IEEE Proc. Computer Vision and Pattern Recognition, CVPR’99, pages: 326-332, IEEE, Fort Collins, CO, 1999 (inproceedings)

pdf video [BibTex]

pdf video [BibTex]

1996


Cardboard people: A parameterized model of articulated motion
Cardboard people: A parameterized model of articulated motion

Ju, S. X., Black, M. J., Yacoob, Y.

In 2nd Int. Conf. on Automatic Face- and Gesture-Recognition, pages: 38-44, Killington, Vermont, October 1996 (inproceedings)

Abstract
We extend the work of Black and Yacoob on the tracking and recognition of human facial expressions using parameterized models of optical flow to deal with the articulated motion of human limbs. We define a "cardboard person model" in which a person's limbs are represented by a set of connected planar patches. The parameterized image motion of these patches is constrained to enforce articulated motion and is solved for directly using a robust estimation technique. The recovered motion parameters provide a rich and concise description of the activity that can be used for recognition. We propose a method for performing view-based recognition of human activities from the optical flow parameters that extends previous methods to cope with the cyclical nature of human motion. We illustrate the method with examples of tracking human legs over long image sequences.

pdf [BibTex]

1996

pdf [BibTex]


Skin and Bones: Multi-layer, locally affine, optical flow and regularization with transparency
Skin and Bones: Multi-layer, locally affine, optical flow and regularization with transparency

(Nominated: Best paper)

Ju, S., Black, M. J., Jepson, A. D.

In IEEE Conf. on Computer Vision and Pattern Recognition, CVPR’96, pages: 307-314, San Francisco, CA, June 1996 (inproceedings)

pdf [BibTex]

pdf [BibTex]


EigenTracking: Robust matching and tracking of articulated objects using a view-based representation
EigenTracking: Robust matching and tracking of articulated objects using a view-based representation

Black, M. J., Jepson, A.

In Proc. Fourth European Conf. on Computer Vision, ECCV’96, pages: 329-342, LNCS 1064, Springer Verlag, Cambridge, England, April 1996 (inproceedings)

pdf video [BibTex]

pdf video [BibTex]


Mixture Models for Image Representation
Mixture Models for Image Representation

Jepson, A., Black, M.

PRECARN ARK Project Technical Report ARK96-PUB-54, March 1996 (techreport)

Abstract
We consider the estimation of local greylevel image structure in terms of a layered representation. This type of representation has recently been successfully used to segment various objects from clutter using either optical ow or stereo disparity information. We argue that the same type of representation is useful for greylevel data in that it allows for the estimation of properties for each of several different components without prior segmentation. Our emphasis in this paper is on the process used to extract such a layered representation from a given image In particular we consider a variant of the EM algorithm for the estimation of the layered model and consider a novel technique for choosing the number of layers to use. We briefly consider the use of a simple version of this approach for image segmentation and suggest two potential applications to the ARK project

pdf [BibTex]

pdf [BibTex]

1995


Robust estimation of multiple surface shapes from occluded textures
Robust estimation of multiple surface shapes from occluded textures

Black, M. J., Rosenholtz, R.

In International Symposium on Computer Vision, pages: 485-490, Miami, FL, November 1995 (inproceedings)

pdf [BibTex]

1995

pdf [BibTex]


no image
The PLAYBOT Project

Tsotsos, J. K., Dickinson, S., Jenkin, M., Milios, E., Jepson, A., Down, B., Amdur, E., Stevenson, S., Black, M., Metaxas, D., Cooperstock, J., Culhane, S., Nuflo, F., Verghese, G., Wai, W., Wilkes, D., Ye, Y.

In Proc. IJCAI Workshop on AI Applications for Disabled People, Montreal, August 1995 (inproceedings)

abstract [BibTex]

abstract [BibTex]


Recognizing facial expressions under rigid and non-rigid facial motions using local parametric models of image motion
Recognizing facial expressions under rigid and non-rigid facial motions using local parametric models of image motion

Black, M. J., Yacoob, Y.

In International Workshop on Automatic Face- and Gesture-Recognition, Zurich, July 1995 (inproceedings)

video abstract [BibTex]

video abstract [BibTex]


Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion
Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion

Black, M. J., Yacoob, Y.

In Fifth International Conf. on Computer Vision, ICCV’95, pages: 347-381, Boston, MA, June 1995 (inproceedings)

Abstract
This paper explores the use of local parametrized models of image motion for recovering and recognizing the non-rigid and articulated motion of human faces. Parametric flow models (for example affine) are popular for estimating motion in rigid scenes. We observe that within local regions in space and time, such models not only accurately model non-rigid facial motions but also provide a concise description of the motion in terms of a small number of parameters. These parameters are intuitively related to the motion of facial features during facial expressions and we show how expressions such as anger, happiness, surprise, fear, disgust and sadness can be recognized from the local parametric motions in the presence of significant head motion. The motion tracking and expression recognition approach performs with high accuracy in extensive laboratory experiments involving 40 subjects as well as in television and movie sequences.

pdf video publisher site [BibTex]

pdf video publisher site [BibTex]


no image
A computational model for shape from texture for multiple textures

Black, M. J., Rosenholtz, R.

Investigative Ophthalmology and Visual Science Supplement, Vol. 36, No. 4, pages: 2202, March 1995 (conference)

abstract [BibTex]

abstract [BibTex]

1993


Mixture models for optical flow computation
Mixture models for optical flow computation

Jepson, A., Black, M.

In IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-93, pages: 760-761, New York, NY, June 1993 (inproceedings)

Abstract
The computation of optical flow relies on merging information available over an image patch to form an estimate of 2-D image velocity at a point. This merging process raises many issues. These include the treatment of outliers in component velocity measurements and the modeling of multiple motions within a patch which arise from occlusion boundaries or transparency. A new approach for dealing with these issues is presented. It is based on the use of a probabilistic mixture model to explicitly represent multiple motions within a patch. A simple extension of the EM-algorithm is used to compute a maximum likelihood estimate for the various motion parameters. Preliminary experiments indicate that this approach is computationally efficient, and that it can provide robust estimates of the optical flow values in the presence of outliers and multiple motions.

pdf tech report [BibTex]

1993

pdf tech report [BibTex]


A framework for the robust estimation of optical flow
A framework for the robust estimation of optical flow

(Helmholtz Prize)

Black, M. J., Anandan, P.

In Fourth International Conf. on Computer Vision, ICCV-93, pages: 231-236, Berlin, Germany, May 1993 (inproceedings)

Abstract
Most approaches for estimating optical flow assume that, within a finite image region, only a single motion is present. This single motion assumption is violated in common situations involving transparency, depth discontinuities, independently moving objects, shadows, and specular reflections. To robustly estimate optical flow, the single motion assumption must be relaxed. This work describes a framework based on robust estimation that addresses violations of the brightness constancy and spatial smoothness assumptions caused by multiple motions. We show how the robust estimation framework can be applied to standard formulations of the optical flow problem thus reducing their sensitivity to violations of their underlying assumptions. The approach has been applied to three standard techniques for recovering optical flow: area-based regression, correlation, and regularization with motion discontinuities. This work focuses on the recovery of multiple parametric motion models within a region as well as the recovery of piecewise-smooth flow fields and provides examples with natural and synthetic image sequences.

pdf video abstract code [BibTex]

pdf video abstract code [BibTex]


Mixture models for optical flow computation
Mixture models for optical flow computation

Jepson, A., Black, M.

In Partitioning Data Sets, DIMACS Workshop, pages: 271-286, (Editors: Ingemar Cox, Pierre Hansen, and Bela Julesz), AMS Pub, Providence, RI., April 1993 (incollection)

pdf [BibTex]

pdf [BibTex]


Action, representation, and purpose: Re-evaluating the foundations of computational vision
Action, representation, and purpose: Re-evaluating the foundations of computational vision

Black, M. J., Aloimonos, Y., Brown, C. M., Horswill, I., Malik, J., G. Sandini, , Tarr, M. J.

In International Joint Conference on Artificial Intelligence, IJCAI-93, pages: 1661-1666, Chambery, France, 1993 (inproceedings)

pdf [BibTex]

pdf [BibTex]

1990


A model for the detection of motion over time
A model for the detection of motion over time

Black, M. J., Anandan, P.

In Proc. Int. Conf. on Computer Vision, ICCV-90, pages: 33-37, Osaka, Japan, December 1990 (inproceedings)

Abstract
We propose a model for the recovery of visual motion fields from image sequences. Our model exploits three constraints on the motion of a patch in the environment: i) Data Conservation: the intensity structure corresponding to an environmental surface patch changes gradually over time; ii) Spatial Coherence: since surfaces have spatial extent neighboring points have similar motions; iii) Temporal Coherence: the direction and velocity of motion for a surface patch changes gradually. The formulation of the constraints takes into account the possibility of multiple motions at a particular location. We also present a highly parallel computational model for realizing these constraints in which computation occurs locally, knowledge about the motion increases over time, and occlusion and disocclusion boundaries are estimated. An implementation of the model using a stochastic temporal updating scheme is described. Experiments with both synthetic and real imagery are presented.

pdf [BibTex]

1990

pdf [BibTex]


Constraints for the early detection of discontinuity from motion
Constraints for the early detection of discontinuity from motion

Black, M. J., Anandan, P.

In Proc. National Conf. on Artificial Intelligence, AAAI-90, pages: 1060-1066, Boston, MA, 1990 (inproceedings)

Abstract
Surface discontinuities are detected in a sequence of images by exploiting physical constraints at early stages in the processing of visual motion. To achieve accurate early discontinuity detection we exploit five physical constraints on the presence of discontinuities: i) the shape of the sum of squared differences (SSD) error surface in the presence of surface discontinuities; ii) the change in the shape of the SSD surface due to relative surface motion; iii) distribution of optic flow in a neighborhood of a discontinuity; iv) spatial consistency of discontinuities; V) temporal consistency of discontinuities. The constraints are described, and experimental results on sequences of real and synthetic images are presented. The work has applications in the recovery of environmental structure from motion and in the generation of dense optic flow fields.

pdf [BibTex]

pdf [BibTex]