← Search

Yushi Zhu

2 accepted papers

2021

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

ICCV 2021poster

Point clouds can be represented in many forms (views), typically, point-based sets, voxel-based cells or range-based images(i.e., panoramic view). The point-based view is geometrically accurate, but it is disordered, which makes it difficult to find local neighbors efficiently. The voxel-based view…

Cited by 333PDFScholar
2021

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

ICCV 2021poster

Recently, various works that attempted to introduce rotation invariance to point cloud analysis have devised point-pair features, such as angles and distances. In these methods, however, the point-pair is only comprised of the center point and its adjacent points in a vicinity, which may bring infor…

Cited by 46PDFScholar