Zobrazeno 1 - 10
of 1 981
pro vyhledávání: '"Wang, HongSheng"'
Current 3D human motion reconstruction methods from monocular videos rely on features within the current reconstruction window, leading to distortion and deformations in the human structure under local occlusions or blurriness in video frames. To est
Externí odkaz:
http://arxiv.org/abs/2411.04399
In real-world road scenes, diverse material properties lead to complex light reflection phenomena, making accurate color reproduction crucial for enhancing the realism and safety of simulated driving environments. However, existing methods often stru
Externí odkaz:
http://arxiv.org/abs/2405.13097
Autor:
Wang, Hongsheng, Cai, Xiang, Sun, Xi, Yue, Jinhong, Tang, Zhanyun, Zhang, Shengyu, Lin, Feng, Wu, Fei
Single-view clothed human reconstruction holds a central position in virtual reality applications, especially in contexts involving intricate human motions. It presents notable challenges in achieving realistic clothing deformation. Current methodolo
Externí odkaz:
http://arxiv.org/abs/2405.12806
Autor:
Wang, Hongsheng, Zhang, Lizao, Zhong, Zhangnan, Xu, Shuolin, Zhou, Xinrui, Zhang, Shengyu, Xu, Huahao, Wu, Fei, Lin, Feng
Reconstructing 3D human bodies from realistic motion sequences remains a challenge due to pervasive and complex occlusions. Current methods struggle to capture the dynamics of occluded body parts, leading to model penetration and distorted motion. Re
Externí odkaz:
http://arxiv.org/abs/2405.12724
In the animation industry, 3D modelers typically rely on front and back non-overlapped concept designs to guide the 3D modeling of anime characters. However, there is currently a lack of automated approaches for generating anime characters directly f
Externí odkaz:
http://arxiv.org/abs/2405.12505
Autor:
Wang, Hongsheng, Zhang, Weiyue, Liu, Sihao, Zhou, Xinrui, Li, Jing, Tang, Zhanyun, Zhang, Shengyu, Wu, Fei, Lin, Feng
Although 3D Gaussian Splatting (3DGS) has recently made progress in 3D human reconstruction, it primarily relies on 2D pixel-level supervision, overlooking the geometric complexity and topological relationships of different body parts. To address thi
Externí odkaz:
http://arxiv.org/abs/2405.12477
Autor:
Wang, Hongsheng1 (AUTHOR), An, Huaming2,3 (AUTHOR) huaming.an@kust.edu.cn, Yang, Bingbing2 (AUTHOR)
Publikováno v:
Fire (2571-6255). Nov2024, Vol. 7 Issue 11, p410. 24p.
Autor:
Wang, Hongsheng1 (AUTHOR) cumming.an@gmail.com, An, Huaming2,3 (AUTHOR) huaming.an@kust.edu.cn, Zhang, Xin2 (AUTHOR)
Publikováno v:
Fire (2571-6255). Nov2024, Vol. 7 Issue 11, p414. 21p.
Prototype learning and decoder construction are the keys for few-shot segmentation. However, existing methods use only a single prototype generation mode, which can not cope with the intractable problem of objects with various scales. Moreover, the o
Externí odkaz:
http://arxiv.org/abs/2210.00765
Publikováno v:
In International Immunopharmacology 5 December 2024 142 Part B