Hi, this is Chuxin Wang.

Biography

Hi! I am a PhD student in Department of Automation at University of Science and Technology of China, advised by Prof. Weiren Wu and Tianzhu Zhang.

My research primarily focuses on 3D computer vision, including point cloud representation learning, point cloud completion, point cloud detection, and point cloud segmentation.

Previously, I interned with the Visual Computing Group at Microsoft Research Asia (2020-2021) and Deep Space Exploration Laboratory (2023-2024).

News 🔥

Jan. 2025: State Space Model Meets Transformer: A New Paradigm for 3D Object Detection was accepted by ICLR 2025.
Dec. 2024: RMAE3D: Rethinking Masked Representation Learning for 3D Point Cloud Understanding was accepted by TIP 2025.
Aug. 2024: Pamba: Enhancing Global Interaction in Point Clouds via State Space Model was accepted by AAAI 2025.
Oct. 2023: Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection were accepted by ICCV 2023.
Oct. 2023: Query Refinement Transformer for 3D Instance Segmentation were accepted by ICCV 2023.
Apr. 2023: SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence were accepted by CVPR 2023.
May. 2023: Long-Short Range Adaptive Transformer With Dynamic Sampling for 3D Object Detection were accepted by TCSVT 2023.

Experiences 📖

Feb. 2022 - Now: Algorithm development intern, DSEL

Sep. 2021 - Now: PhD Student, USTC

Jul. 2020 - Jun. 2021: Research intern, MSRA (VC Group)

Sep. 2017 - Jun. 2021: Undergraduate, USTC

Publications

* denotes equal contribution. More publications can be found in Google Scholar.

	"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection" Chuxin Wang, Wenfei Yang, Xiang Liu, Tianzhu Zhang International Conference on Learning Representations (ICLR), 2025 [Paper] [Webpage] [Code] [Poster] [BibTeX]
	"Rethinking Masked Representation Learning for 3D Point Cloud Understanding" Chuxin Wang, Yixin Zha, Jianfeng He, Wenfei Yang, Tianzhu Zhang IEEE Transactions on Image Processing (TIP), 2025 [Paper] [Webpage] [Code] [BibTeX]
	"Pamba: Enhancing Global Interaction in Point Clouds via State Space Model" Zhuoyuan Li, Yubo Ai, Jiahao Lu, Chuxin Wang, Jiacheng Deng, Hanzhi Chang, Yanzhe Liang, Wenfei Yang, Shifeng Zhang, Tianzhu Zhang Association for the Advancement of Artificial Intelligence (AAAI), 2025 [Paper]
	"Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection" Chuxin Wang, Wenfei Yang, Tianzhu Zhang International Conference on Computer Vision 2023 (ICCV), 2023 [Paper] [Webpage] [Code] [BibTeX]
	"QRT3D: Query Refinement Transformer for 3D Instance Segmentation" Jiahao Lu, Jiacheng Deng, Chuxin Wang, Jianfeng He, Tianzhu Zhang International Conference on Computer Vision 2023 (ICCV), 2023 [Paper]
	"Long-short Range Adaptive Transformer with Dynamic Sampling for 3D Object Detection" Chuxin Wang, Jiacheng Deng, Jianfeng He, Tianzhu Zhang, Zhe Zhang, Yongdong Zhang IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023 [Paper] [Webpage] [BibTeX]
	"SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence" Jiacheng Deng, Chuxin Wang, Jiahao Lu, Jianfeng He, Tianzhu Zhang, Jiyang Yu, Zhe Zhang Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [Paper] [Webpage] [Code] [BibTeX] [Poster]
	"Style-based Point Generator with Adversarial Rendering for Point Cloud Completion" Chulin Xie, Chuxin Wang, Bo Zhang, Hao Yang, Dong Chen, Fang Wen Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [Paper] [Webpage] [Code] [BibTeX] [Poster]
	"ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation" Ruijie Zhu, Chuxin Wang, Ziyang Song, Li Liu, Tianzhu Zhang, Yongdong Zhang Arxiv, 2024 [Paper] [Webpage] [Code]
	"EC-Depth: Exploring the consistency of self-supervised monocular depth estimation under challenging scenes" Ziyang Song, Ruijie Zhu, Chuxin Wang, Jiacheng Deng, Jianfeng He, Tianzhu Zhang ArXiv, 2023 [Paper] [Webpage] [Code]