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]

2004


no image
Automatic spike sorting for neural decoding

Wood, F. D., Fellows, M., Donoghue, J. P., Black, M. J.

In Proc. IEEE Engineering in Medicine and Biology Society, pages: 4009-4012, September 2004 (inproceedings)

pdf [BibTex]

2004

pdf [BibTex]


Closed-loop neural control of cursor motion using a {Kalman} filter
Closed-loop neural control of cursor motion using a Kalman filter

Wu, W., Shaikhouni, A., Donoghue, J. P., Black, M. J.

In Proc. IEEE Engineering in Medicine and Biology Society, pages: 4126-4129, September 2004 (inproceedings)

pdf [BibTex]

pdf [BibTex]


The dense estimation of motion and appearance in layers
The dense estimation of motion and appearance in layers

Yalcin, H., Black, M. J., Fablet, R.

In IEEE Workshop on Image and Video Registration, June 2004 (inproceedings)

pdf [BibTex]

pdf [BibTex]


{3D} human limb detection using space carving and multi-view eigen models
3D human limb detection using space carving and multi-view eigen models

Bhatia, S., Sigal, L., Isard, M., Black, M. J.

In IEEE Workshop on Articulated and Nonrigid Motion, June 2004 (inproceedings)

pdf [BibTex]

pdf [BibTex]


Tracking loose-limbed people
Tracking loose-limbed people

Sigal, L., Bhatia, S., Roth, S., Black, M. J., Isard, M.

In IEEE Conf. on Computer Vision and Pattern Recognition, 1, pages: 421-428, June 2004 (inproceedings)

pdf [BibTex]

pdf [BibTex]


Gibbs likelihoods for {Bayesian} tracking
Gibbs likelihoods for Bayesian tracking

Roth, S., Sigal, L., Black, M. J.

In IEEE Conf. on Computer Vision and Pattern Recognition, 1, pages: 886-893, June 2004 (inproceedings)

pdf [BibTex]

pdf [BibTex]


no image
A direct brain-machine interface for 2D cursor control using a Kalman filter

Shaikhouni, A., Wu, W., Moris, D. S., Donoghue, J. P., Black, M. J.

Society for Neuroscience, 2004, Online (conference)

abstract [BibTex]

abstract [BibTex]

2000


Stochastic tracking of {3D} human figures using {2D} image motion
Stochastic tracking of 3D human figures using 2D image motion

(Winner of the 2010 Koenderink Prize for Fundamental Contributions in Computer Vision)

Sidenbladh, H., Black, M. J., Fleet, D.

In European Conference on Computer Vision, ECCV, pages: 702-718, LNCS 1843, Springer Verlag, Dublin, Ireland, June 2000 (inproceedings)

Abstract
A probabilistic method for tracking 3D articulated human figures in monocular image sequences is presented. Within a Bayesian framework, we define a generative model of image appearance, a robust likelihood function based on image gray level differences, and a prior probability distribution over pose and joint angles that models how humans move. The posterior probability distribution over model parameters is represented using a discrete set of samples and is propagated over time using particle filtering. The approach extends previous work on parameterized optical flow estimation to exploit a complex 3D articulated motion model. It also extends previous work on human motion tracking by including a perspective camera model, by modeling limb self occlusion, and by recovering 3D motion from a monocular sequence. The explicit posterior probability distribution represents ambiguities due to image matching, model singularities, and perspective projection. The method relies only on a frame-to-frame assumption of brightness constancy and hence is able to track people under changing viewpoints, in grayscale image sequences, and with complex unknown backgrounds.

pdf code [BibTex]

2000

pdf code [BibTex]


no image
Functional analysis of human motion data

Ormoneit, D., Hastie, T., Black, M. J.

In In Proc. 5th World Congress of the Bernoulli Society for Probability and Mathematical Statistics and 63rd Annual Meeting of the Institute of Mathematical Statistics, Guanajuato, Mexico, May 2000 (inproceedings)

[BibTex]

[BibTex]


no image
Stochastic modeling and tracking of human motion

Ormoneit, D., Sidenbladh, H., Black, M. J., Hastie, T.

Learning 2000, Snowbird, UT, April 2000 (conference)

abstract [BibTex]

abstract [BibTex]


A framework for modeling the appearance of {3D} articulated figures
A framework for modeling the appearance of 3D articulated figures

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

In Int. Conf. on Automatic Face and Gesture Recognition, pages: 368-375, Grenoble, France, March 2000 (inproceedings)

pdf [BibTex]

pdf [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]