Zobrazeno 1 - 10
of 127
pro vyhledávání: '"He, Yisheng"'
Autor:
Li, Zhe, Yuan, Weihao, He, Yisheng, Qiu, Lingteng, Zhu, Shenhao, Gu, Xiaodong, Shen, Weichao, Dong, Yuan, Dong, Zilong, Yang, Laurence T.
Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP's pretraining on static image-
Externí odkaz:
http://arxiv.org/abs/2410.07093
Autor:
Yuan, Weihao, Shen, Weichao, He, Yisheng, Dong, Yuan, Gu, Xiaodong, Dong, Zilong, Bo, Liefeng, Huang, Qixing
Motion generation from discrete quantization offers many advantages over continuous regression, but at the cost of inevitable approximation errors. Previous methods usually quantize the entire body pose into one code, which not only faces the difficu
Externí odkaz:
http://arxiv.org/abs/2409.17686
Autor:
Cai, Junhao, Yang, Yuji, Yuan, Weihao, He, Yisheng, Dong, Zilong, Bo, Liefeng, Cheng, Hui, Chen, Qifeng
This paper studies the problem of estimating physical properties (system identification) through visual observations. To facilitate geometry-aware guidance in physical property estimation, we introduce a novel hybrid framework that leverages 3D Gauss
Externí odkaz:
http://arxiv.org/abs/2406.14927
This paper enables high-fidelity, transferable NeRF editing by frequency decomposition. Recent NeRF editing pipelines lift 2D stylization results to 3D scenes while suffering from blurry results, and fail to capture detailed structures caused by the
Externí odkaz:
http://arxiv.org/abs/2404.02514
This paper studies a new open-set problem, the open-vocabulary category-level object pose and size estimation. Given human text descriptions of arbitrary novel object categories, the robot agent seeks to predict the position, orientation, and size of
Externí odkaz:
http://arxiv.org/abs/2403.12396
Autor:
Chen, Minglin, Yuan, Weihao, Wang, Yukun, Sheng, Zhe, He, Yisheng, Dong, Zilong, Bo, Liefeng, Guo, Yulan
Recently, text-to-3D approaches have achieved high-fidelity 3D content generation using text description. However, the generated objects are stochastic and lack fine-grained control. Sketches provide a cheap approach to introduce such fine-grained co
Externí odkaz:
http://arxiv.org/abs/2401.14257
6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models. In this work, we study a new open set problem; the
Externí odkaz:
http://arxiv.org/abs/2203.14628
In this work, we tackle the challenging problem of category-level object pose and size estimation from a single depth image. Although previous fully-supervised works have demonstrated promising performance, collecting ground-truth pose labels is gene
Externí odkaz:
http://arxiv.org/abs/2203.02884
Autor:
Zhu, Yong, Wu, Bingmin, Xia, Songyan, Zheng, Guangzhen, Cheng, Juanjuan, Huang, Song, Xiong, Qingping, Chen, Jing, Li, Hailun, Hirao, Hajime, He, Yisheng, Chen, Jihang
Publikováno v:
In Chemical Engineering Journal 15 November 2024 500
Autor:
Wang, Xi, Meng, Xiao, Cui, Tongtong, Hu, Qian, Jin, Bowen, He, Yisheng, Zhu, Xingjun, Ye, Chunhong
Publikováno v:
In Carbohydrate Polymers 1 October 2024 341