Zobrazeno 1 - 10
of 276
pro vyhledávání: '"Hilliges, Otmar"'
Classifier-free guidance (CFG) is crucial for improving both generation quality and alignment between the input condition and final output in diffusion models. While a high guidance scale is generally required to enhance these aspects, it also causes
Externí odkaz:
http://arxiv.org/abs/2410.02416
Autor:
Bühler, Marcel C., Li, Gengyan, Wood, Erroll, Helminger, Leonhard, Chen, Xu, Shah, Tanmay, Wang, Daoye, Garbin, Stephan, Orts-Escolano, Sergio, Hilliges, Otmar, Lagun, Dmitry, Riviere, Jérémy, Gotardo, Paulo, Beeler, Thabo, Meka, Abhimitra, Sarkar, Kripasindhu
Volumetric modeling and neural radiance field representations have revolutionized 3D face capture and photorealistic novel view synthesis. However, these methods often require hundreds of multi-view input images and are thus inapplicable to cases wit
Externí odkaz:
http://arxiv.org/abs/2410.00630
Autor:
Guo, Chen, Jiang, Tianjian, Kaufmann, Manuel, Zheng, Chengwei, Valentin, Julien, Song, Jie, Hilliges, Otmar
While previous years have seen great progress in the 3D reconstruction of humans from monocular videos, few of the state-of-the-art methods are able to handle loose garments that exhibit large non-rigid surface deformations during articulation. This
Externí odkaz:
http://arxiv.org/abs/2409.15269
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
Despite progress in human motion capture, existing multi-view methods often face challenges in estimating the 3D pose and shape of multiple closely interacting people. This difficulty arises from reliance on accurate 2D joint estimations, which are h
Externí odkaz:
http://arxiv.org/abs/2408.02110
Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion model or modifying the traini
Externí odkaz:
http://arxiv.org/abs/2407.02687
Autor:
Zhang, Daiwei, Li, Gengyan, Li, Jiajie, Bressieux, Mickaël, Hilliges, Otmar, Pollefeys, Marc, Van Gool, Luc, Wang, Xi
Human activities are inherently complex, often involving numerous object interactions. To better understand these activities, it is crucial to model their interactions with the environment captured through dynamic changes. The recent availability of
Externí odkaz:
http://arxiv.org/abs/2406.19811
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
Autor:
Jiang, Zeren, Guo, Chen, Kaufmann, Manuel, Jiang, Tianjian, Valentin, Julien, Hilliges, Otmar, Song, Jie
We present MultiPly, a novel framework to reconstruct multiple people in 3D from monocular in-the-wild videos. Reconstructing multiple individuals moving and interacting naturally from monocular in-the-wild videos poses a challenging task. Addressing
Externí odkaz:
http://arxiv.org/abs/2406.01595