As camera and LiDAR sensors capture complementary information in autonomous driving,
great efforts have been made to conduct semantic segmentation through multi-modality data …

Pre-training by numerous image data has become de-facto for robust 2D representations. In
contrast, due to the expensive data processing, a paucity of 3D datasets severely hinders …

This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view
images. Many previous works have shown impressive reconstruction results on textured …

Learning distinctive point-wise features is critical for low-overlap point cloud registration.
Recently, it has achieved huge success in incorporating Transformer into point cloud feature …

Performing 3D dense captioning and visual grounding requires a common and shared
understanding of the underlying multimodal relationships. However, despite some previous …

Despite significant advancements in monocular depth estimation for static images,
estimating video depth in the open world remains challenging, since open-world videos are …

Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for
LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera …

Abstract 3D point-clouds and 2D images are different visual representations of the physical
world. While human vision can understand both representations, computer vision models …

Recent advances in 3D perception have shown impressive progress in understanding
geometric structures of 3D shapes and even scenes. Inspired by these advances in …

Knowledge distillation, which aims to transfer the knowledge learned by a cumbersome
teacher model to a lightweight student model, has become one of the most popular and …