pic

Welcome to Yongwei Nie's Website

Yongwei Nie is now an Associate Professor at the School of Computer Science and Engineering of South China University of Technology, Guangzhou, Guangdong, China, 510006. He received his doctor and bachelor degree from Computer School of Wuhan Univesrity in 2015 and in 2009. His research interests fall in Computer Graphics and Computer Vision. Contact him via nieyongwei@scut.edu.cn.
 
Students

News
  • 12/2024: Papers accepted to AAAI 2025, TMM.
  • 11/2024: One paper accepted to IJCV.
  • 09/2024: One paper accepted to NeurIPS 2024.
  • 09/2024: One paper accepted to CVIU.
  • 06/2024: Two Papers accepted to ECCV 2024.
  • 06/2024: Papers accepted to CVM 2024, Graphical Models, TCSVT, TMM, TNNLS, and TVCG.
  • 07/2023: One paper accepted to TVCG.
  • 05/2023: One paper accepted to IJCV.
  • 03/2023: One paper accepted to SIGGRAPH 2023.
  • 02/2023: Two papers accepted to CVPR 2023.
  • 06/2022: Papers accepted to ACM MM 2022, EGSR 2022, ChinaGraph 2022, PG 2022.
  • 03/2022: One paper accepted to CVPR 2022.
  • 12/2021: One paper accepted to CVM 2022.
  • 08/2021: One paper accepted to SIGGRAPH Asia 2021.
  • 07/2021: One paper accepted to CCF CAD/CG 2021.
  • 07/2021: Two papers accepted to ICCV 2021.
  • 03/2021: A paper accepted to TMM.
  • 01/2021: A paper accepted to TOG.
  • 07/2020: A paper accepted to TMM.
  • 03/2020: Paper "Enhancing Underexposed Photos using Perceptually Bidirectional Similarity" has been accepted by TMM.
  • 11/2019: Paper "Video Super-Resolution via Pre-Frame Constrained and Deep-Feature Enhanced Sparse Reconstruction" has been accepted by Pattern Recognition.
  • 11/2019: Paper "Deep Camouflage Images" has been accepted by AAAI.
  • 09/2019: Paper "Collision-Free Video Synopsis Incorporating Object Speed and Size Changes" has been accepted by TIP.
  • 08/2019: Paper "Multi-View Video Synopsis via Simultaneous Object-Shifting and View-Switching Optimization" has been accepted by TIP.
  • 08/2019: Paper "Dual Illumination Estimation for Robust Exposure Correction" has been accepted by Pacific Graphics 2019.
  • 2019/06/13: Code of "Effective Video Stabilization via Joint Trajectory Smoothing and Frame Warping" is available.
  • 06/2019: Paper "Effective Video Stabilization via Joint Trajectory Smoothing and Frame Warping" has been accepted by TVCG.
  • 02/2019: Paper "Interactive Contour Extraction via Sketch-Alike Dense-Validation Optimization" has been accepted by TCSVT.
  • 01/2018: Code of "Dynamic Video Stitching via Shakiness Removing" is available.
  • 09/2017: Paper "Multi-video Object Synopsis Integrating Optimal View Switching" has been accepted by Siggraph Asia 2017 Technical Briefs.
 
Education and Work Experience
  1. 2019/09 -                        Associate Professor                                     South China University of Technology
  2. 2018/09 - 2019/08          Associate Researcher                                 South China University of Technology
  3. 2017/09 - 2018/08          Postdoctoral Associate Researcher             South China University of Technology
  4. 2015/07 - 2017/08          Postdoc (with Prof. Guiqing Li)                    South China University of Technology
  5. 2009/09 - 2015/06          PhD (with Prof. Chunxia Xiao)                     Wuhan University
  6. 2005/09 - 2009/06          Bachelor                                                       Wuhan University
 
Selected Publications (* corresponding author) (Google Scholar DBLP)

  • Jian Zhu, Jianrong Yan, Jiebin Huang, Yongwei Nie*, Bin Sheng, Tong-Yee Lee
    SGG-Nets: Generic Rotation-Invariant Plugin Networks for Point Cloud Analysis
    IEEE Transactions on Multimedia (TMM), accepted.

  • Rongjia Zheng, Qing Zhang, Yongwei Nie, Wei-Shi Zheng
    When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data
    AAAI 2025, accepted.

  • Yuhui Deng, Yuqin Lu, Yangyang Xu, Yongwei Nie, Shengfeng He
    Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation
    AAAI 2025, accepted.

  • Yongwei Nie, Wei Ge, Siming Zeng, Qing Zhang, Guiqing Li, Ping Li, Hongmin Cai
    Occlusion-Preserved Surveillance Video Synopsis with Flexible Object Graph
    International Journal of Computer Vision (IJCV). Accepted, 2024.

  • Yongwei Nie, Mingxian Fan, Chengjiang Long, Qing Zhang, Jian Zhu, Xuemiao Xu
    Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
    Proceedings of the thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), Vancouver, Canada, Dec 9-15, 2024.
    Code coming soon.

  • Qiuxia Lai, Yongwei Nie*, Yu Li, Hanqiu Sun, Qiang Xu
    Information bottleneck approach to spatial attention learning
    Computer Vision and Image Understanding (CVIU), accepted.

  • Xiaoqi Sheng, Hongmin Cai, Yongwei Nie, Shengfeng He, Yiu-Ming Cheung, Jiazhou Chen
    Modality-Aware Discriminative Fusion Network for Integrated Analysis of Brain Imaging Genomics
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), accepted.

  • Wenju Xu, Chengjiang Long, Yongwei Nie, Guanghui Wang
    Disentangled Representation Learning for Controllable Person Image Generation
    IEEE Transactions on Multimedia (TMM), accepted.

  • Yongwei Nie, Changzhen Liu, Chengjiang Long, Qing Zhang, Guiqing Li, Hongmin Cai
    Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses
    Proceedings of the 18th European Conference on Computer Vision (ECCV), MILAN, Italy, 29 Sep. - 04 Oct., 2024.
    Code.

  • Yongwei Nie, Hao Huang, Chengjiang Long, Qing Zhang, Pradipta Maji, Hongmin Cai
    Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection
    Proceedings of the 18th European Conference on Computer Vision (ECCV), MILAN, Italy, 29 Sep. - 04 Oct., 2024.
    Code.

  • Yongwei Nie, Jiaqi Yu, Chengjiang Long, Qing Zhang, Guiqing Li, Hongmin Cai
    Single-Image SVBRDF Estimation Using Auxiliary Renderings as Intermediate Targets
    IEEE Transactions on Visualization and Computer Graphics (TVCG), accepted.
    Project Page, Code Author's PDF

  • Chengxing Lin, Wenju Xu, Jian Zhu*, Yongwei Nie*, Ruichu Cai, Xuemiao Xu
    PatchMixing Masked Autoencoders for 3D Point Cloud Self-Supervised Learning
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), DOI: 10.1109/TCSVT.2024.3405069

  • Yongwei Nie, Meihua Zhao, Qing Zhang, Ping Li, Jian Zhu, Hongmin Cai
    Make Static Person Walk Again via Separating Pose Action from Shape
    Proceedings of the 12th International Conference on Computational Visual Media (CVM 2024), Wellington, New Zealand, 10-12 April, 2024. (Accepted to Graphical Models.)

  • Yongwei Nie, Rong Pan, Qing Zhang, Xuemiao Xu, Guiqing Li, Hongmin Cai
    Face Expression Recognition via Product-Cross Dual Attention and Neutral-Aware Anchor Loss
    Proceedings of the 12th International Conference on Computational Visual Media (CVM 2024), Wellington, New Zealand, 10-12 April, 2024. (LNCS,volume 14593.)

  • Qiwei Sun, Yongwei Nie, Qing Zhang, Guiqing Li
    Building Coarse to Fine Convex Hulls with Auxiliary Vertices for Palette-based Image Recoloring
    IEEE Transactions on Visualization and Computer Graphics (TVCG), DOI:10.1109/TVCG.2023.3296386.

  • 唐福梅,聂勇伟*,余嘉祺,张青,李桂清
    基于伪时空图卷积网络修复姿态引导的Transformer行人视频修复方法
    ChinaGraph 2022,西宁.
    计算机辅助设计与图形学学报, 36(4), 2024.

  • Hao Jiang, Qing Zhang, Yongwei Nie, Lei Zhu, and Wei-Shi Zheng
    Learning to Remove Shadows from a Single Image
    International Journal of Computer Vision (IJCV), Volume 131, pages 2471–2488, 2023.

  • Qing Zhang, Hao Jiang, Yongwei Nie, Wei-Shi Zheng
    Pyramid Texture Filtering
    ACM SIGGRAPH, Los Angeles, USA, Aug 6-10, 2023.
    ACM Transactions on Graphics (TOG), 42(4), 2023.
    Project Page.

  • Zhian Liu, Maomao Li, Yong Zhang, Cairong Wang, Qi Zhang, Jue Wang, Yongwei Nie*
    Fine-Grained Face Swapping via Regional GAN Inversion
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, June 18-22, 2023.
    Project Page.

  • Wenju Xu, Chengjiang Long, Yongwei Nie
    Learning Dynamic Style Kernels for Artistic Style Transfer
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, June 18-22, 2023.

  • Hao Jiang, Qing Zhang, Yongwei Nie, Lei Zhu, Wei-Shi Zheng
    Learning Multi-Scale Deep Image Prior for High-Quality Unsupervised Image Denoising
    Computer Graphics Forum, 41(7), 2022.
    Proceedings of Pacific Graphics 2022.

  • Lingwei Dang, Yongwei Nie*, Chengjiang Long, Qing Zhang, Guiqing Li
    Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
    Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), Lisbon, Portugal, Oct 10-14, 2022.
    Paper PyTorch Jittor.

  • Wangziwei Jiang, Guiqing Li, Yongwei Nie, Chuhua Xian
    GPU-Driven Real-Time Mesh Contour Vectorization
    Proceedings of the 33rd Eurographics Symposium on Rendering (EGSR), Prague, Czech Republic, Jul 4-6, 2022.

  • Tiezheng Ma, Yongwei Nie*, Chengjiang Long, Qing Zhang, Guiqing Li
    Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 19-24 June, 2022.
    Paper Code.

  • Qing Zhang, Yongwei Nie, Lei Zhu, Wei-Shi Zheng
    High-Quality Unsupervised Image Denoising via Multi-Scale Deep Image Prior
    Proceedings of the 10th International Conference on Computational Visual Media (CVM), Beijing, 7-9 April, 2022.

  • 杨韫韬,聂勇伟*,张青,李平,李桂清
    基于RNN和注意力机制的双向人体姿态补全方法
    CCF CAD/CG 2021 最佳论文,大连.
    计算机辅助设计与图形学学报,34(11), 2022.
    Code.

  • Jiaqi Yu, Yongwei Nie*, Chengjiang Long, Wenju Xu, Qing Zhang, Guiqing Li
    Monte Carlo Denoising via Auxiliary Feature Guided Self-Attention
    Proceedings of the ACM SIGGRAPH Conference and Exhibition in Asia (SIGGRAPH Asia), Tokyo, Japan, Dec 14-17, 2021.
    ACM Transactions on Graphics (TOG), 40(6), 2021.
    Paper Code Project Page.

  • Lingwei Dang, Yongwei Nie*, Chengjiang Long, Qing Zhang, Guiqing Li
    MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
    Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, Oct 11-17, 2021.
    Paper Code.

  • Zhian Liu, Yongwei Nie*, Chengjiang Long, Qing Zhang, Guiqing Li
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
    Proceedings of the IEEE International Conference on Computer Vision (ICCV oral), Montreal, Canada, Oct 11-17, 2021.
    Paper Code.

  • Qing Zhang, Yongwei Nie, Lei Zhu, Chunxia Xiao, Wei-Shi Zheng
    A Blind Color Separation Model for Faithful Palette-based Image Recoloring
    IEEE Transactions on Multimedia (TMM). 24: 1545 - 1557, 2022.

  • Yupan Wang, Guiqing Li, Huiqian Zhang, Xinyi Zou, Yuxin Liu, Yongwei Nie
    PanoMan: Sparse Localized Components Based Model for Full Human Motions
    ACM Transactions on Graphics (TOG). 40(2): Article 19, 2021. PDF

  • Qiuxia Lai, Salman Khan, Yongwei Nie*, Hanqiu Sun, Jianbing Shen, Ling Shao
    Understanding More about Human and Machine Attention in Deep Neural Networks
    IEEE Transactions on Multimedia (TMM). Vol. 23, 2086-2099, 2021.

  • Qing Zhang, Yongwei Nie, Lei Zhu, Chunxia Xiao, Wei-Shi Zheng
    Enhancing Underexposed Photos using Perceptually Bidirectional Similarity
    IEEE Transactions on Multimedia (TMM). Vol. 23, 189-202, 2021.

  • Qiuxia Lai, Yongwei Nie*, Hanqiu Sun, Qiang Xu, Zhensong Zhang, Mingyu Xiao
    Video Super-Resolution via Pre-Frame Constrained and Deep-Feature Enhanced Sparse Reconstruction
    Pattern Recognition (PR). Vol. 100, 107139, 2020.

  • Qing Zhang, Gelin Yin, Yongwei Nie, Wei-Shi Zheng
    Deep Camouflage Images
    AAAI Conference on Artificial Intelligence (AAAI) 2020.

  • Yongwei Nie, Zhenkai Li, Zhensong Zhang, Qing Zhang, Tiezheng Ma, Hanqiu Sun
    Collision-Free Video Synopsis Incorporating Object Speed and Size Changes
    IEEE Transactions on Image Processing (TIP). Vol. 29, 1465-1478, 2020.
    Code Video.

  • Zhensong Zhang, Yongwei Nie*, Hanqiu Sun, Qing Zhang, Qiuxia Lai, Guiqing Li, Mingyu Xiao
    Multi-View Video Synopsis via Simultaneous Object-Shifting and View-Switching Optimization
    IEEE Transactions on Image Processing (TIP). Vol. 29, 971-985, 2020.
    Code Video.

  • Tiezheng Ma, Yongwei Nie*, Qing Zhang, Zhensong Zhang, Hanqiu Sun, Guiqing Li
    Effective Video Stabilization via Joint Trajectory Smoothing and Frame Warping
    IEEE Transactions on Visualization and Computer Graphics (TVCG). 26(11): 3163-3176, 2020
    Code Video 1 Video 2.

  • Yongwei Nie, Xu Cao, Ping Li, Qing Zhang, Zhensong Zhang, Guiqing Li, Hanqiu Sun
    Interactive Contour Extraction via Sketch-Alike Dense-Validation Optimization
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). Vol. 30, No. 4, 903-916, 2020.
    Code.

  • Qing Zhang, Yongwei Nie, Wei-Shi Zheng
    Dual Illumination Estimation for Robust Exposure Correction
    Computer Graphics Forum (CGF). 38(7): 243-252, 2019.
    Proceedings of Pacific Graphics 2019.

  • 曹旭,聂勇伟*,李桂清
    高精度连续人脸轮廓提取
    计算机辅助设计与图形学学报, 2019, 31(4): 522-530.

  • Yongwei Nie, Tan Su, Zhensong Zhang, Hanqiu Sun, Guiqing Li
    Dynamic Video Stitching via Shakiness Removing
    IEEE Transactions on Image Processing (TIP). Vol. 27, No. 1, 164-178, 2018.
    Code Video.

  • Yongwei Nie, Zhensong Zhang, Hanqiu Sun, Tan Su, Guiqing Li
    Homography Propagation and Optimization for Wide-baseline Street Image Interpolation
    IEEE Transactions on Visualization and Computer Graphics (TVCG). Vol. 23, No. 10, 2328-2341, 2017.
    Code Video.

  • Zhensong Zhang, Yongwei Nie*, Hanqiu Sun, Qiuxia Lai, Guiqing Li
    Multi-video Object Synopsis Integrating Optimal View Switching
    Siggraph Asia Technical Briefs, Thailand, 2017.

  • Qing Zhang, Yongwei Nie, Ling Zhang, Chunxia Xiao
    Underexposed Video Enhancement via Perception-driven Progressive Fusion
    IEEE Transactions on Visualization and Computer Graphics (TVCG). Vol. 22, No. 6, 1773-1785, 2016.

  • Tan Su, Yongwei Nie*, Zhensong Zhang, Hanqiu Sun, Guiqing Li
    Video Stitching for Handheld Inputs via Combined Video Stabilization
    SIGGRAPH Asia ’16 Technical Briefs, December 05-08, 2016, Macao.

  • 徐超,聂勇伟*,葛红美,周国富
    基于新视角合成的视频摘要交互式浏览
    电子学报. 2015, 43(11): 2263-2270.

  • Yongwei Nie, Hanqiu Sun, Ping Li, Chunxia Xiao, Kwan-Liu Ma
    Object Movements Synopsis via Part Assembling and Stitching
    IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol. 20, No. 9, 1303-1315, 2014.

  • Yongwei Nie, Chunxia Xiao, Hanqiu Sun, Ping Li
    Compact Video Synopsis via Global Spatiotemporal Optimization
    IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol. 19, No. 10, 1664-1676, 2013.

  • Yongwei Nie, Qing Zhang, Renfang Wang, Chunxia Xiao
    Video Retargeting Combining Warping and Summarizing Optimization
    The Visual Computer, Vol. 29, No. 6-8, 785-794, 2013.

  • Chunxia Xiao, Yongwei Nie, Feng Tang
    Efficient Edit Propagation Using Hierarchical Data Structure
    IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol. 17, No. 8, 1135-1147, 2011.

  • Chunxia Xiao, Meng Liu, Yongwei Nie, Zhao Dong
    Fast Exact Nearest Patch Match for Patch-based Image Editing and Processing
    IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol. 17, No. 8, 1122-1134, 2011.

  • Chunxia Xiao, Yongwei Nie, Wei Hua and Wenting Zheng
    Fast multi-scale joint bilateral texture upsampling
    The Visual Computer, Vol. 26, No. 4, 263-275, 2010.

  • 肖春霞,聂勇伟,黄先锋,赵勇,彭群生
    基于联合双边滤波的纹理合成上采样算法
    计算机学报,2009,32(02):241-251.
 
Visiting
  • 2014/02 - 2014/08, Research Associate, with Prof. Hongbo Fu, SCM, CityU.
  • 2013/07 - 2013/08, Research Assistant, with Prof. Hanqiu Sun, CSE, CUHK.
  • 2012/10 - 2012/12, Visiting Graphics and Geometric Computing Group, with Prof. Shi-Min Hu, Tsinghua University.
  • 2012/03 - 2012/06, Research Assistant, with Prof. Hanqiu Sun, CSE, CUHK.
  • 2011/04 - 2011/07, Research Assistant, with Prof. Hanqiu Sun, CSE, CUHK.
 
Awards
  • ACM Wuhan Doctoral Dissertation Award 2016.
  • National Scholarship 2013.
  • New PHD Researcher Award by Ministry of Education 2012.
  • Tencent Excellent Scholarship 2010.
  • Outstanding Undergraduate Thesis of Hubei Province 2009.
  • Award of Excellent Graduate of Wuhan University 2009.
  • Best Paper Award of Chinagraph 2008.
  • Tian Yuan Di Ke Scholarship 2008.
  • First Class Scholarship 2008.
  • Second Class Scholarship 2006.