Abstract: Person re-identification (ReID) aims to identify the same individual across different cameras. Most existing researches focus on horizontal perspectives, where cameras and individuals are ...

Official PyTorch implementation of PlatoNeRF (CVPR 2024), a method for recovering 3D geometry from single-view two-bounce lidar measurements. PlatoNeRF learns 3D geometry by reconstructing lidar ...

Official code has be released soon for ECCV 2024 paper AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos. AvatarPose leverages the personalized ...

University of Minnesota researchers developed a 3D-printed scaffold that directs stem cells to grow into functioning nerve cells, successfully restoring movement in rats with severed spinal cords.

Abstract: Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, etc. Inspired by the recent prompt learning in natural language processing ...