1 code implementation • 15 Jun 2023 • Lea Müller, Vickie Ye, Georgios Pavlakos, Michael Black, Angjoo Kanazawa
To address this, we present a novel approach that learns a prior over the 3D proxemics two people in close social interaction and demonstrate its use for single-view 3D reconstruction.
no code implementations • 2 Feb 2023 • Mohamed Hassan, Yunrong Guo, Tingwu Wang, Michael Black, Sanja Fidler, Xue Bin Peng
These scene interactions are learned using an adversarial discriminator that evaluates the realism of a motion within the context of a scene.
no code implementations • ICCV 2021 • Mohamed Hassan, Duygu Ceylan, Ruben Villegas, Jun Saito, Jimei Yang, Yi Zhou, Michael Black
A long-standing goal in computer vision is to capture, model, and realistically synthesize human behavior.
1 code implementation • 31 Aug 2020 • Partha Ghosh, Pravir Singh Gupta, Roy Uziel, Anurag Ranjan, Michael Black, Timo Bolkart
Specifically, we condition StyleGAN2 on FLAME, a generative 3D face model.
4 code implementations • 10 Aug 2020 • Korrawe Karunratanakul, Jinlong Yang, Yan Zhang, Michael Black, Krikamol Muandet, Siyu Tang
Specifically, our generative model is able to synthesize high-quality human grasps, given only on a 3D object point cloud.
4 code implementations • ICLR 2020 • Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, Bernhard Schölkopf
Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models.
no code implementations • ICCV 2019 • Jie Song, Bjoern Andres, Michael Black, Otmar Hilliges, Siyu Tang
The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels of the initial graph and the hard constraints are introduced in the CRF as high-order potentials.
no code implementations • ECCV 2018 • Joel Janai, Fatma Guney, Anurag Ranjan, Michael Black, Andreas Geiger
In this paper, we propose a framework for unsupervised learning of optical flow and occlusions over multiple frames.
1 code implementation • CVPR 2017 • Chao Zhang, Sergi Pujades, Michael Black, Gerard Pons-Moll
We address the problem of estimating human pose and body shape from 3D scans over time.
no code implementations • CVPR 2017 • Judith Bütepage, Michael Black, Danica Kragic, Hedvig Kjellström
To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units.