papers

Publications (120)

cs.CV2022

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

Zhaoyang Lyu, Zhifeng Kong, Xudong Xu +2

3D point cloud is an important 3D representation for capturing real world 3D objects. However, real-scanned 3D point clouds are often incomplete, and it is important to recover com…

cs.CV2023

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Lingdong Kong, Jiawei Ren, Liang Pan +1

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised lear…

cs.CV2026

EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

Wenjia Wang, Liang Pan, Huaijin Pi +8

Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting.…

cs.CV2023

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Youquan Liu, Lingdong Kong, Jun Cen +5

Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a novel fram…

cs.CV2021

Variational Relational Point Completion Network

Liang Pan, Xinyi Chen, Zhongang Cai +4

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise. Existing point cloud completion methods tend to generate global shape skeletons and hence lac…

math.NA2016

A Third-order Compact Gas-kinetic Scheme on Unstructured Meshes for Compressible Navier-Stokes Solutions

Liang Pan, Kun Xu

In this paper, for the first time a compact third-order gas-kinetic scheme is proposed on unstructured meshes for the compressible viscous flow computations. The possibility to de…