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


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 (1) the generated human bodies should be semantically plausible with the 3D environment, e.g. people sitting on the sofa or cooking near the stove; (2) the generated human-scene interaction should be physically feasible in the way 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 pose 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.

PDF link (url) [BibTex]

PDF link (url) [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]


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]

1998


The Digital Office: Overview
The Digital Office: Overview

Black, M., Berard, F., Jepson, A., Newman, W., Saund, E., Socher, G., Taylor, M.

In AAAI Spring Symposium on Intelligent Environments, pages: 1-6, Stanford, March 1998 (inproceedings)

pdf [BibTex]

1998

pdf [BibTex]


A framework for modeling appearance change in image sequences
A framework for modeling appearance change in image sequences

Black, M. J., Fleet, D. J., Yacoob, Y.

In Sixth International Conf. on Computer Vision, ICCV’98, pages: 660-667, Mumbai, India, January 1998 (inproceedings)

Abstract
Image "appearance" may change over time due to a variety of causes such as 1) object or camera motion; 2) generic photometric events including variations in illumination (e.g. shadows) and specular reflections; and 3) "iconic changes" which are specific to the objects being viewed and include complex occlusion events and changes in the material properties of the objects. We propose a general framework for representing and recovering these "appearance changes" in an image sequence as a "mixture" of different causes. The approach generalizes previous work on optical flow to provide a richer description of image events and more reliable estimates of image motion.

pdf video [BibTex]

pdf video [BibTex]


Parameterized modeling and recognition of activities
Parameterized modeling and recognition of activities

Yacoob, Y., Black, M. J.

In Sixth International Conf. on Computer Vision, ICCV’98, pages: 120-127, Mumbai, India, January 1998 (inproceedings)

Abstract
A framework for modeling and recognition of temporal activities is proposed. The modeling of sets of exemplar activities is achieved by parameterizing their representation in the form of principal components. Recognition of spatio-temporal variants of modeled activities is achieved by parameterizing the search in the space of admissible transformations that the activities can undergo. Experiments on recognition of articulated and deformable object motion from image motion parameters are presented.

pdf [BibTex]

pdf [BibTex]


Motion feature detection using steerable flow fields
Motion feature detection using steerable flow fields

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

In IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-98, pages: 274-281, IEEE, Santa Barbara, CA, 1998 (inproceedings)

Abstract
The estimation and detection of occlusion boundaries and moving bars are important and challenging problems in image sequence analysis. Here, we model such motion features as linear combinations of steerable basis flow fields. These models constrain the interpretation of image motion, and are used in the same way as translational or affine motion models. We estimate the subspace coefficients of the motion feature models directly from spatiotemporal image derivatives using a robust regression method. From the subspace coefficients we detect the presence of a motion feature and solve for the orientation of the feature and the relative velocities of the surfaces. Our method does not require the prior computation of optical flow and recovers accurate estimates of orientation and velocity.

pdf [BibTex]

pdf [BibTex]


Visual surveillance of human activity
Visual surveillance of human activity

L. Davis, S. F., Harwood, D., Yacoob, Y., Hariatoglu, I., Black, M.

In Asian Conference on Computer Vision, ACCV, 1998 (inproceedings)

pdf [BibTex]

pdf [BibTex]


A Probabilistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions
A Probabilistic framework for matching temporal trajectories: Condensation-based recognition of gestures and expressions

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

In European Conf. on Computer Vision, ECCV-98, pages: 909-924, Freiburg, Germany, 1998 (inproceedings)

pdf [BibTex]

pdf [BibTex]


Recognizing temporal trajectories using the {Condensation} algorithm
Recognizing temporal trajectories using the Condensation algorithm

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

In Int. Conf. on Automatic Face and Gesture Recognition, pages: 16-21, Nara, Japan, 1998 (inproceedings)

pdf [BibTex]

pdf [BibTex]

1997


Robust anisotropic diffusion and sharpening of scalar and vector images
Robust anisotropic diffusion and sharpening of scalar and vector images

Black, M. J., Sapiro, G., Marimont, D., Heeger, D.

In Int. Conf. on Image Processing, ICIP, 1, pages: 263-266, Vol. 1, Santa Barbara, CA, October 1997 (inproceedings)

Abstract
Relations between anisotropic diffusion and robust statistics are described. We show that anisotropic diffusion can be seen as a robust estimation procedure that estimates a piecewise smooth image from a noisy input image. The "edge-stopping" function in the anisotropic diffusion equation is closely related to the error norm and influence function in the robust estimation framework. This connection leads to a new "edge-stopping" function based on Tukey's biweight robust estimator, that preserves sharper boundaries than previous formulations and improves the automatic stopping of the diffusion. The robust statistical interpretation also provides a means for detecting the boundaries (edges) between the piecewise smooth regions in the image. We extend the framework to vector-valued images and show applications to robust image sharpening.

pdf publisher site [BibTex]

1997

pdf publisher site [BibTex]


Robust anisotropic diffusion: Connections between robust statistics, line processing, and anisotropic diffusion
Robust anisotropic diffusion: Connections between robust statistics, line processing, and anisotropic diffusion

Black, M. J., Sapiro, G., Marimont, D., Heeger, D.

In Scale-Space Theory in Computer Vision, Scale-Space’97, pages: 323-326, LNCS 1252, Springer Verlag, Utrecht, the Netherlands, July 1997 (inproceedings)

pdf [BibTex]

pdf [BibTex]


Learning parameterized models of image motion
Learning parameterized models of image motion

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

In IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-97, pages: 561-567, Puerto Rico, June 1997 (inproceedings)

Abstract
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that are computed from a training set using principal component analysis. Many complex image motions can be represented by a linear combination of a small number of these basis flows. The learned motion models may be used for optical flow estimation and for model-based recognition. For optical flow estimation we describe a robust, multi-resolution scheme for directly computing the parameters of the learned flow models from image derivatives. As examples we consider learning motion discontinuities, non-rigid motion of human mouths, and articulated human motion.

pdf [BibTex]

pdf [BibTex]


Analysis of gesture and action in technical talks for video indexing
Analysis of gesture and action in technical talks for video indexing

Ju, S. X., Black, M. J., Minneman, S., Kimber, D.

In IEEE Conf. on Computer Vision and Pattern Recognition, pages: 595-601, CVPR-97, Puerto Rico, June 1997 (inproceedings)

Abstract
In this paper, we present an automatic system for analyzing and annotating video sequences of technical talks. Our method uses a robust motion estimation technique to detect key frames and segment the video sequence into subsequences containing a single overhead slide. The subsequences are stabilized to remove motion that occurs when the speaker adjusts their slides. Any changes remaining between frames in the stabilized sequences may be due to speaker gestures such as pointing or writing and we use active contours to automatically track these potential gestures. Given the constrained domain we define a simple ``vocabulary'' of actions which can easily be recognized based on the active contour shape and motion. The recognized actions provide a rich annotation of the sequence that can be used to access a condensed version of the talk from a web page.

pdf [BibTex]

pdf [BibTex]


Modeling appearance change in image sequences
Modeling appearance change in image sequences

Black, M. J., Yacoob, Y., Fleet, D. J.

In Advances in Visual Form Analysis, pages: 11-20, Proceedings of the Third International Workshop on Visual Form, Capri, Italy, May 1997 (inproceedings)

abstract [BibTex]

abstract [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]

1991


Dynamic motion estimation and feature extraction over long image sequences
Dynamic motion estimation and feature extraction over long image sequences

Black, M. J., Anandan, P.

In Proc. IJCAI Workshop on Dynamic Scene Understanding, Sydney, Australia, August 1991 (inproceedings)

[BibTex]

1991

[BibTex]


Robust dynamic motion estimation over time
Robust dynamic motion estimation over time

(IEEE Computer Society Outstanding Paper Award)

Black, M. J., Anandan, P.

In Proc. Computer Vision and Pattern Recognition, CVPR-91,, pages: 296-302, Maui, Hawaii, June 1991 (inproceedings)

Abstract
This paper presents a novel approach to incrementally estimating visual motion over a sequence of images. We start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of the minimization problem. The resulting objective function is non-convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task. We present a highly parallel incremental stochastic minimization algorithm which has a number of advantages over previous approaches. The incremental nature of the scheme makes it truly dynamic and permits the detection of occlusion and disocclusion boundaries.

pdf video abstract [BibTex]

pdf video abstract [BibTex]