The metaverse is a visual world that blends the physical world and digital world. At present,
the development of the metaverse is still in the early stage, and there lacks a framework for …

The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

Emerging neural radiance fields (NeRF) are a promising scene representation for computer
graphics, enabling high-quality 3D reconstruction and novel view synthesis from image …

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This
appealing ability is vital for recognition and understanding. To enable such capability in AI …

We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the
memory and computational cost, existing point-based pipelines usually adopt task-agnostic …

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point-
or voxel-based methods as they often yield better performance than the traditional range …

The robustness of 3D perception systems under natural corruptions from environments and
sensors is pivotal for safety-critical applications. Existing large-scale 3D perception datasets …

Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …

Video restoration aims to restore high-quality frames from low-quality frames. Different from
single image restoration, video restoration generally requires to utilize temporal information …

Autonomous driving is regarded as one of the most promising remedies to shield human
beings from severe crashes. To this end, 3D object detection serves as the core basis of …