Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Ren, Daxuan"'
This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differentiable comp
Externí odkaz:
http://arxiv.org/abs/2407.15686
Autor:
Cheng, Wei, Chen, Ruixiang, Yin, Wanqi, Fan, Siming, Chen, Keyu, He, Honglin, Luo, Huiwen, Cai, Zhongang, Wang, Jingbo, Gao, Yang, Yu, Zhengming, Lin, Zhengyu, Ren, Daxuan, Yang, Lei, Liu, Ziwei, Loy, Chen Change, Qian, Chen, Wu, Wayne, Lin, Dahua, Dai, Bo, Lin, Kwan-Yee
Realistic human-centric rendering plays a key role in both computer vision and computer graphics. Rapid progress has been made in the algorithm aspect over the years, yet existing human-centric rendering datasets and benchmarks are rather impoverishe
Externí odkaz:
http://arxiv.org/abs/2307.10173
Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning the shape given in the form of point clouds by inverse sketch-and-extrude. We present ExtrudeNet, an unsupervised end-t
Externí odkaz:
http://arxiv.org/abs/2209.15632
Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the reconstruction by exploiting the gen
Externí odkaz:
http://arxiv.org/abs/2207.10061
Autor:
Cai, Zhongang, Ren, Daxuan, Zeng, Ailing, Lin, Zhengyu, Yu, Tao, Wang, Wenjia, Fan, Xiangyu, Gao, Yang, Yu, Yifan, Pan, Liang, Hong, Fangzhou, Zhang, Mingyuan, Loy, Chen Change, Yang, Lei, Liu, Ziwei
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. With the advances of new sensors and algorithms, there is an increasing demand for more versatile datasets. In this work, we contribute HuMMan, a l
Externí odkaz:
http://arxiv.org/abs/2204.13686
Autor:
Cai, Zhongang, Zhang, Mingyuan, Ren, Jiawei, Wei, Chen, Ren, Daxuan, Lin, Zhengyu, Zhao, Haiyu, Yang, Lei, Loy, Chen Change, Liu, Ziwei
Image- and video-based 3D human recovery (i.e., pose and shape estimation) have achieved substantial progress. However, due to the prohibitive cost of motion capture, existing datasets are often limited in scale and diversity. In this work, we obtain
Externí odkaz:
http://arxiv.org/abs/2110.07588
Autor:
Ren, Daxuan, Zheng, Jianmin, Cai, Jianfei, Li, Jiatong, Jiang, Haiyong, Cai, Zhongang, Zhang, Junzhe, Pan, Liang, Zhang, Mingyuan, Zhao, Haiyu, Yi, Shuai
Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised end-to-end network for learning shapes from point clouds and discovering
Externí odkaz:
http://arxiv.org/abs/2108.11305
Autor:
Cai, Zhongang, Zhang, Junzhe, Ren, Daxuan, Yu, Cunjun, Zhao, Haiyu, Yi, Shuai, Yeo, Chai Kiat, Loy, Chen Change
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly complex, containing multiple object instances that could be identical
Externí odkaz:
http://arxiv.org/abs/2007.14878
Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-degree sweep, without extensiv
Externí odkaz:
http://arxiv.org/abs/2006.16796
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence [IEEE Trans Pattern Anal Mach Intell] 2024 Aug 27; Vol. PP. Date of Electronic Publication: 2024 Aug 27.