Zobrazeno 1 - 10
of 376
pro vyhledávání: '"Lin Jiahao"'
In this paper, we tackle the challenging task of learning a generalizable human NeRF model from a monocular video. Although existing generalizable human NeRFs have achieved impressive results, they require muti-view images or videos which might not b
Externí odkaz:
http://arxiv.org/abs/2308.16576
Autor:
Zhang, Gongjie, Lin, Jiahao, Wu, Shuang, Song, Yilin, Luo, Zhipeng, Xue, Yang, Lu, Shijian, Wang, Zuoguan
Vectorized high-definition (HD) map is essential for autonomous driving, providing detailed and precise environmental information for advanced perception and planning. However, current map vectorization methods often exhibit deviations, and the exist
Externí odkaz:
http://arxiv.org/abs/2306.10502
Autor:
Huang, Jiayuan, Liu, Sanxin, Li, Peijie, Wei, Lei, Lin, Gan, Lin, Jiahao, Luo, Yuting, Liu, Yixin, Mao, Yudan, Ruan, Hengfang, Qin, Bing, Fan, Ping, Lu, Tingting, Cai, Wei, Yi, Haotong, Mou, Xiangyu, Lu, Zhengqi, Zhao, Wenjing, Wu, Aimin
Publikováno v:
In Pharmacological Research October 2024 208
Publikováno v:
In The Veterinary Journal December 2024 308
Autor:
Liu, Yang, Pan, Wanbing, Li, Lingyu, Gong, Jianquan, Dong, Hongjing, Zhang, Bin, Lin, Jiahao, Zheng, Zhenjia
Publikováno v:
In Food Chemistry Advances December 2024 5
Publikováno v:
In Information Processing in Agriculture March 2024 11(1):14-25
Autor:
Lin, Jiahao, Lee, Gim Hee
Bottom-up approaches for image-based multi-person pose estimation consist of two stages: (1) keypoint detection and (2) grouping of the detected keypoints to form person instances. Current grouping approaches rely on learned embedding from only visua
Externí odkaz:
http://arxiv.org/abs/2104.02385
Autor:
Lin, Jiahao, Lee, Gim Hee
Existing approaches for multi-view multi-person 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views and solve for the 3D pose estimation for each person. Establishing cross-view co
Externí odkaz:
http://arxiv.org/abs/2104.02273
Publikováno v:
In Journal of Ethnopharmacology 30 January 2024 319 Part 3
Autor:
Lin, Jiahao, Lee, Gim Hee
Current works on multi-person 3D pose estimation mainly focus on the estimation of the 3D joint locations relative to the root joint and ignore the absolute locations of each pose. In this paper, we propose the Human Depth Estimation Network (HDNet),
Externí odkaz:
http://arxiv.org/abs/2007.08943