Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Yao, Chun-Han"'
We present Stable Video 4D (SV4D), a latent video diffusion model for multi-frame and multi-view consistent dynamic 3D content generation. Unlike previous methods that rely on separately trained generative models for video generation and novel view s
Externí odkaz:
http://arxiv.org/abs/2407.17470
Autor:
Voleti, Vikram, Yao, Chun-Han, Boss, Mark, Letts, Adam, Pankratz, David, Tochilkin, Dmitry, Laforte, Christian, Rombach, Robin, Jampani, Varun
We present Stable Video 3D (SV3D) -- a latent video diffusion model for high-resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent work on 3D generation propose techniques to adapt 2D generative models for novel view
Externí odkaz:
http://arxiv.org/abs/2403.12008
Autor:
Pesavento, Marco, Xu, Yuanlu, Sarafianos, Nikolaos, Maier, Robert, Wang, Ziyan, Yao, Chun-Han, Volino, Marco, Boyer, Edmond, Hilton, Adrian, Tung, Tony
Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover
Externí odkaz:
http://arxiv.org/abs/2403.10357
Autor:
Yao, Chun-Han, Raj, Amit, Hung, Wei-Chih, Li, Yuanzhen, Rubinstein, Michael, Yang, Ming-Hsuan, Jampani, Varun
Estimating 3D articulated shapes like animal bodies from monocular images is inherently challenging due to the ambiguities of camera viewpoint, pose, texture, lighting, etc. We propose ARTIC3D, a self-supervised framework to reconstruct per-instance
Externí odkaz:
http://arxiv.org/abs/2306.04619
Autor:
Yao, Chun-Han, Hung, Wei-Chih, Li, Yuanzhen, Rubinstein, Michael, Yang, Ming-Hsuan, Jampani, Varun
Automatically estimating 3D skeleton, shape, camera viewpoints, and part articulation from sparse in-the-wild image ensembles is a severely under-constrained and challenging problem. Most prior methods rely on large-scale image datasets, dense tempor
Externí odkaz:
http://arxiv.org/abs/2212.11042
Estimating 3D human pose and shape from 2D images is a crucial yet challenging task. While prior methods with model-based representations can perform reasonably well on whole-body images, they often fail when parts of the body are occluded or outside
Externí odkaz:
http://arxiv.org/abs/2208.10652
Autor:
Yao, Chun-Han, Hung, Wei-Chih, Li, Yuanzhen, Rubinstein, Michael, Yang, Ming-Hsuan, Jampani, Varun
Creating high-quality articulated 3D models of animals is challenging either via manual creation or using 3D scanning tools. Therefore, techniques to reconstruct articulated 3D objects from 2D images are crucial and highly useful. In this work, we pr
Externí odkaz:
http://arxiv.org/abs/2207.03434
Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision tasks. Unlike
Externí odkaz:
http://arxiv.org/abs/2108.07792
Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually close to geometric primitives and thus ar
Externí odkaz:
http://arxiv.org/abs/2107.13629
Autor:
Hsu, Han-Kai, Yao, Chun-Han, Tsai, Yi-Hsuan, Hung, Wei-Chih, Tseng, Hung-Yu, Singh, Maneesh, Yang, Ming-Hsuan
Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribut
Externí odkaz:
http://arxiv.org/abs/1910.11319