Point-, voxel-, and range-views are three representative forms of point
...
Recent advancements in vision foundation models (VFMs) have opened up ne...
Vision foundation models such as Contrastive Vision-Language Pre-trainin...
The robustness of 3D perception systems under natural corruptions from
e...
Training deep models for semantic scene completion (SSC) is challenging ...
LiDAR segmentation is crucial for autonomous driving perception. Recent
...
LiDAR-camera fusion methods have shown impressive performance in 3D obje...
Contrastive language-image pre-training (CLIP) achieves promising result...