no code implementations • 25 Apr 2024 • Jiamin Wu, Kenkun Liu, Han Gao, Xiaoke Jiang, Lei Zhang
By harnessing the benefits of 3D Gaussians, our approach offers an efficient and accurate solution for 3D reconstruction from single-view images.
no code implementations • 20 Oct 2022 • Jianqiu Chen, Mingshan Sun, Ye Zheng, Tianpeng Bao, Zhenyu He, Donghai Li, Guoqiang Jin, Rui Zhao, Liwei Wu, Xiaoke Jiang
Numerous 6D pose estimation methods have been proposed that employ end-to-end regression to directly estimate the target pose parameters.
no code implementations • 15 Aug 2022 • Mingshan Sun, Ye Zheng, Tianpeng Bao, Jianqiu Chen, Guoqiang Jin, Liwei Wu, Rui Zhao, Xiaoke Jiang
Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images.
no code implementations • CVPR 2022 • Xiaoke Jiang, Donghai Li, Hao Chen, Ye Zheng, Rui Zhao, Liwei Wu
They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion.