Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Kanazawa, Angjoo"'
Self-occlusion is common when capturing people in the wild, where the performer do not follow predefined motion scripts. This challenges existing monocular human reconstruction systems that assume full body visibility. We introduce Self-Occluded Avat
Externí odkaz:
http://arxiv.org/abs/2410.23800
We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns natural behav
Externí odkaz:
http://arxiv.org/abs/2410.16259
Autor:
Yi, Brent, Ye, Vickie, Zheng, Maya, Müller, Lea, Pavlakos, Georgios, Ma, Yi, Malik, Jitendra, Kanazawa, Angjoo
We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that ca
Externí odkaz:
http://arxiv.org/abs/2410.03665
Autor:
Kerr, Justin, Kim, Chung Min, Wu, Mingxuan, Yi, Brent, Wang, Qianqian, Goldberg, Ken, Kanazawa, Angjoo
Humans can learn to manipulate new objects by simply watching others; providing robots with the ability to learn from such demonstrations would enable a natural interface specifying new behaviors. This work develops Robot See Robot Do (RSRD), a metho
Externí odkaz:
http://arxiv.org/abs/2409.18121
Autor:
Ye, Vickie, Li, Ruilong, Kerr, Justin, Turkulainen, Matias, Yi, Brent, Pan, Zhuoyang, Seiskari, Otto, Ye, Jianbo, Hu, Jeffrey, Tancik, Matthew, Kanazawa, Angjoo
gsplat is an open-source library designed for training and developing Gaussian Splatting methods. It features a front-end with Python bindings compatible with the PyTorch library and a back-end with highly optimized CUDA kernels. gsplat offers numero
Externí odkaz:
http://arxiv.org/abs/2409.06765
Autor:
Maluleke, Vongani, Müller, Lea, Rajasegaran, Jathushan, Pavlakos, Georgios, Ginosar, Shiry, Kanazawa, Angjoo, Malik, Jitendra
This paper asks to what extent social interaction influences one's behavior. We study this in the setting of two dancers dancing as a couple. We first consider a baseline in which we predict a dancer's future moves conditioned only on their past moti
Externí odkaz:
http://arxiv.org/abs/2409.04440
Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches are limited in that they either depend on templates, are effective only in quasi-static scenes, or
Externí odkaz:
http://arxiv.org/abs/2407.13764
Novel view synthesis from unconstrained in-the-wild image collections remains a significant yet challenging task due to photometric variations and transient occluders that complicate accurate scene reconstruction. Previous methods have approached the
Externí odkaz:
http://arxiv.org/abs/2407.12306
Autor:
McAllister, David, Ge, Songwei, Huang, Jia-Bin, Jacobs, David W., Efros, Alexei A., Holynski, Aleksander, Kanazawa, Angjoo
Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in
Externí odkaz:
http://arxiv.org/abs/2406.09417
Autor:
Weber, Ethan, Peterlinz, Riley, Mathur, Rohan, Warburg, Frederik, Efros, Alexei A., Kanazawa, Angjoo
In this work, we recover the underlying 3D structure of non-geometrically consistent scenes. We focus our analysis on hand-drawn images from cartoons and anime. Many cartoons are created by artists without a 3D rendering engine, which means that any
Externí odkaz:
http://arxiv.org/abs/2405.10320