no code implementations • 12 Mar 2024 • Qihang Fang, Chengcheng Tang, Shugao Ma, Yanchao Yang
Skeleton-based motion representations are robust for action localization and understanding for their invariance to perspective, lighting, and occlusion, compared with images.
1 code implementation • NeurIPS 2023 • Qihang Fang, Yafei Song, Keqiang Li, Liefeng Bo
The key is a rendering method that is only based on the density field.
1 code implementation • 10 Apr 2023 • Qihang Fang, Yafei Song, Keqiang Li, Li Shen, Huaiyu Wu, Gang Xiong, Liefeng Bo
From this insight, given a reconstructed density field and observation images, we design a closed-form method to approximate the color field with low-frequency spherical harmonics, and compute the inverse mean residual color.
1 code implementation • 8 Dec 2020 • Qihang Fang, Yingda Yin, Qingnan Fan, Fei Xia, Siyan Dong, Sheng Wang, Jue Wang, Leonidas Guibas, Baoquan Chen
These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale.