Wenxiao Zhang

Wenxiao Zhang

Hohai university

I’m currently an Associate Researcher at the College of Computer Science and Software Engineering, Hohai University, Nanjing, China. I earned my Ph.D. from the School of Computer Science, Wuhan University, China, in 2020. From 2021 to 2023, I was a Research Fellow at Singapore University of Technology and Design, working with Prof. Jun Liu. Subsequently, I served as an Associate Researcher at the School of Information Science and Technology, University of Science and Technology of China, Hefei, China, from 2023 to 2024, before joining Hohai University in 2025. I have published 20+ papers in venues like CVPR, ECCV, ICCV, and TVCG, with over 700 citations.

My research interest includes:

  • 3D scene localization and navigation
  • 3D content editing and generation
  • Point cloud analysis

  • 3D reconstruction

🏭 Work Experience

  • 2016 - 2017, R\&D Engineer, Inspur International Co., Ltd., Jinan China.
  • 2020 - 2023, Research Fellow, Singapore University of Technology and Design, Singapore.
  • 2024 - 2025, Associate Researcher University of Science and Technology of China, Hefei China.
  • 2025 - now, Associate Professor, Hohai University, Hefei China.

🎓 Educations

  • 2017 - 2020, PHD, School of Computer Science, Wuhan University, Wuhan, China. Advisor: Chunxia Xiao.

  • 2014 - 2016, Master, School of Computer Science, Huazhong University of Science and Technology, Wuhan China. Advisor: Dan Li.

  • 2010 - 2014, Bechelor, School of Information Engineering, Shandong Normal University, Jinan, China.

📝 Publications

*indicates corresponding author; +indicates co-first author.

2025

  • Y Xu, H Qu, J Liu, Wenxiao Zhang*, X Yang*. CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework. CVPR 2025. (CCF A) [Paper] [Codes]

  • Wenxiao Zhang, Rahmani, H., & Liu, J. Unpaired 3d shape-to-shape translation via gradient-guided triplane diffusion. IEEE Transactions on Visualization and Computer Graphics. IEEE Transactions on Visualization and Computer Graphics 2025. (CCF A) [Paper] [Codes]

2024

  • Xu, Hang, Long, Chen, Wenxiao Zhang*, Liu, Yuan, Cao, Zhen, Dong, Zhen, Yang, Bisheng. Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion. ECCV 2024. [Paper] [Codes]

  • Wenxiao Zhang, Wang, Z., Xu, L., Yang, X., Liu, J*. Informative Point cloud Dataset Extraction for Classification via Gradient-based Points Moving. ACM Multimedia. ACM Multimedia 2024. (CCF A) [Paper] [Codes]

  • Wenxiao Zhang, Rahmani, H., Yang, X., Liu, J*.Reverse2Complete: Unpaired Multimodal Point Cloud Completion via Guided Diffusion. ACM Multimedia 2024. (CCF A) [Paper] [Codes]

  • Chen Long, Wenxiao Zhang, Zhe Chen, Haiping Wang, Yuan Liu, Peiling Tong, Zhen Cao, Zhen Dong, Bisheng Yang. SparseDC: depth completion from sparse and non-uniform inputs. Information Fusion 2024. (SCI Q1) [Paper] [Codes]

  • Yusen Wang, Kaixuan Zhou, Wenxiao Zhang, Chunxia Xiao. MegaSurf: Scalable Large Scene Neural Surface Reconstruction. ACM Multimedia 2024. (CCF A) [Paper]

2023

  • Wenxiao Zhang, Zhou, Huajian, Dong, Zhen, Yan, Qingan, Xiao, Chunxia*. Point cloud completion via skeleton-detail transformer. IEEE Transactions on Visualization and Computer Graphics 2023. (CCF A) [Paper] [Codes]

  • Wenxiao, Zhou, Huajian, Dong, Zhen, Yan, Qingan, Xiao, Chunxia*. Rank-pointretrieval: Reranking point cloud retrieval via a visually consistent registration evaluation. IEEE Transactions on Visualization and Computer Graphics 2023. (CCF A) [Paper] [Codes]

  • Cao, Z., Wenxiao Zhang+, Xin, W., Zhen, D., Yushen, L., Xiongwu, X., & Yang, B. Kt-net: Knowledge transfer for unpaired 3d shape completion. AAAI 2023. (CCF A) [Paper] [Codes]

  • Ziqi Wang, Fei Luo, Xiaoxiao Long, Wenxiao Zhang, Chunxia Xiao. Learning long-range information with dual-scale transformers for indoor scene completion. ICCV 2023. [Paper]

  • Tuo Cao, Wenxiao Zhang, Yanping Fu, Shengjie Zheng, Fei Luo, Chunxia Xiao. Dgecn++: A depth-guided edge convolutional network for end-to-end 6d pose estimation via attention mechanism. IEEE Transactions on Circuits and Systems for Video Technology 2023. [Paper]

Before 2023

  • Long, C, Wenxiao Zhang+, Li, R., Wang, H., Dong, Z., & Yang, B. Pc2-pu:Patch correlation and position correction for effective point cloud upsampling. ACM Multimedia.ACM MM 2022. (CCF A) [Paper] [Codes]

  • Wenxiao, Qingan, Yan, Chunxia, Xiao*. Detail preserved point cloud completion via separated feature aggregation. European Conference on Computer Vision. ECCV 2020. [Paper] [Codes]

  • Tuo Cao, Fei Luo, Yanping Fu, Wenxiao Zhang, Shengjie Zheng, Chunxia Xiao. DGECN: A depth-guided edge convolutional network for end-to-end 6D pose estimation. CVPR 2022. (CCF A) [Paper]

  • Wenxiao Zhang, Chunxia Xiao. PCAN: 3D attention map learning using contextual information for point cloud based retrieval. CVPR. 2019. (CCF A) [Paper] [Codes]

💬 Service

  • PC Member/Reviewer for CVPR/ICCV/ECCV/NIPS/ICML/AAAI/ACM MM; TOG/TVCG/TRO/TMM/TCSVT.