😃 Welcome to my personal page!
Hi there . This is Chuandong Liu (刘川东 in Chinese), a PhD student at Captain in Wuhan University since 2023, advised by Prof.Gui-song Xia and Prof.Lei Yu. Before that, I received my B.S. and M.S. degrees from Chongqing University of Posts and Telecommunications, advised by Prof.Chenqiang Gao. My current research interest is 3D Vision.
🔥 News
- 2025-09 : 🎉🎉 MixGS is accepted to NeurIPS 2025.
- 2025-02 : 🎉🎉 AIScene is accepted to CVPR 2025.
- 2023-02 : 🎉🎉 HSSDA is accepted to CVPR 2023.
- 2022-02 : 🎉🎉 SS3D is accepted to CVPR 2022.
📝 Publications
(* denotes equal contribution. )
[NeurIPS 2025] Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation
Chuandong Liu, Huijiao Wang, Lei Yu, Gui-Song Xia
[Project page]
[Paper]
[Code]
[Video]
We present MixGS, a novel holistic optimization framework for large-scale 3D scene reconstruction.
[CVPR 2025] Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation
Chuandong Liu*, Xingxing Weng*, Shuguo Jiang, Pengcheng Li, Lei Yu, Gui-Song Xia.
[Paper]
[Code]
We present AIScene, a intra-scene consistency and inter-scene correlation for semi-supervised LiDAR semantic segmentation.
[CVPR 2023] Hierarchical supervision and shuffle data augmentation for 3d semi-supervised object detection
Chuandong Liu, Chenqiang Gao, Fangcen Liu, Pengcheng Li, Deyu Meng, Xinbo Gao.
[Paper]
[Code]
[Video]
We present the hierarchical supervision strategy and shuffle data augmentation strategy, which can be directly applied to the off-the-shelf 3D semi-supervised point cloud object detector.
[CVPR 22] Ss3d: Sparsely-supervised 3d object detection from point cloud
Chuandong Liu, Chenqiang Gao, Fangcen Liu, Jiang Liu, Deyu Meng, Xinbo Gao.
[Paper]
[Code]
SS3D is a sparsely-supervised 3D object detection method.