Zobrazeno 1 - 10
of 616
pro vyhledávání: '"Black, Michael P."'
Training methods to perform robust 3D human pose and shape (HPS) estimation requires diverse training images with accurate ground truth. While BEDLAM demonstrates the potential of traditional procedural graphics to generate such data, the training im
Externí odkaz:
http://arxiv.org/abs/2411.08663
Autor:
Patel, Priyanka, Black, Michael J.
We address the challenge of accurate 3D human pose and shape estimation from monocular images. The key to accuracy and robustness lies in high-quality training data. Existing training datasets containing real images with pseudo ground truth (pGT) use
Externí odkaz:
http://arxiv.org/abs/2411.08128
Autor:
Zakharov, Egor, Sklyarova, Vanessa, Black, Michael, Nam, Giljoo, Thies, Justus, Hilliges, Otmar
We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians to produce accurate and realistic strand-based reconstructions from multi-view data. In contrast to recent approaches that leverage uns
Externí odkaz:
http://arxiv.org/abs/2409.14778
Autor:
Rong, Boxiang, Grigorev, Artur, Wang, Wenbo, Black, Michael J., Thomaszewski, Bernhard, Tsalicoglou, Christina, Hilliges, Otmar
We introduce Gaussian Garments, a novel approach for reconstructing realistic simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color an
Externí odkaz:
http://arxiv.org/abs/2409.08189
Autor:
Tripathi, Shashank, Taheri, Omid, Lassner, Christoph, Black, Michael J., Holden, Daniel, Stoll, Carsten
Generating realistic human motion is essential for many computer vision and graphics applications. The wide variety of human body shapes and sizes greatly impacts how people move. However, most existing motion models ignore these differences, relying
Externí odkaz:
http://arxiv.org/abs/2409.03944
Autor:
Qiu, Zeju, Liu, Weiyang, Feng, Haiwen, Liu, Zhen, Xiao, Tim Z., Collins, Katherine M., Tenenbaum, Joshua B., Weller, Adrian, Black, Michael J., Schölkopf, Bernhard
Against the backdrop of enthusiasm for large language models (LLMs), there is an urgent need to scientifically assess their capabilities and shortcomings. This is nontrivial in part because it is difficult to find tasks which the models have not enco
Externí odkaz:
http://arxiv.org/abs/2408.08313
The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training dat
Externí odkaz:
http://arxiv.org/abs/2408.00712
Autor:
Gozlan, Yoni, Falisse, Antoine, Uhlrich, Scott, Gatti, Anthony, Black, Michael, Chaudhari, Akshay
Pose estimation has promised to impact healthcare by enabling more practical methods to quantify nuances of human movement and biomechanics. However, despite the inherent connection between pose estimation and biomechanics, these disciplines have lar
Externí odkaz:
http://arxiv.org/abs/2406.09788
Autor:
Albaba, Mert, Christen, Sammy, Langarek, Thomas, Gebhardt, Christoph, Hilliges, Otmar, Black, Michael J.
Reinforcement Learning has achieved significant success in generating complex behavior but often requires extensive reward function engineering. Adversarial variants of Imitation Learning and Inverse Reinforcement Learning offer an alternative by lea
Externí odkaz:
http://arxiv.org/abs/2406.08472
Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body
Externí odkaz:
http://arxiv.org/abs/2405.14869