State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, etc .) often project the point clouds to 2D s…
Symmetric image registration estimates bi-directional spatial transformations between images while enforcing an inverse-consistency. Its capability of eliminating bias introduced inevitably by gene…
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel…
Person re-identification (re-ID) aims to robustly measure visual affinities between person images. It has wide applications in intelligent surveillance by associating same persons' images across mu…