4 papers
3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving
Qipeng Li, Yuan Zhuang, Yiwen Chen +5
For the SLAM system in robotics and autonomous driving, the accuracy of front-end odometry and back-end loop-closure detection determine the whole intelligent system performance. B…
PoseFusion: Robust Object-in-Hand Pose Estimation with SelectLSTM
Yuyang Tu, Junnan Jiang, Shuang Li +3
Accurate estimation of the relative pose between an object and a robot hand is critical for many manipulation tasks. However, most of the existing object-in-hand pose datasets use…
Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images
Liguo Jiang, Miaopeng Li, Jianjie Zhang +4
We introduce an approach that accurately reconstructs 3D human poses and detailed 3D full-body geometric models from single images in realtime. The key idea of our approach is a no…
Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
Miaopeng Li, Zimeng Zhou, Jie Li +1
In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods. Specifically, we perform the network feed-…