Longguang Wang 王龙光

I received my Ph.D. degree from National University of Defense Technology in 2022 and B.Eng degree from Shandong University in 2015. My current research interests include low-level vision and 3D vision.

Email  /  Google Scholar  /  GitHub  /  CV  /  Lab Webpage

News

  • [02/2025] Three papers (VideoDirector, DropoutGS, and SaMam) were accepted by CVPR 2025.
  • [12/2024] One paper (AIQViT) was accepted by AAAI 2025.
  • [12/2024] Two papers about stereo matching were accepted by IEEE TIP.
  • [07/2024] One paper (Tangram-Splatting) was accepted by ACM MM 2024.
  • [07/2024] Three papers (MemE-3DGS/NeRF, FormerStereo and AEDNet) were accepted by ECCV 2024.
  • [05/2024] Our paper ''Unsupervised Degradation Representation Learning for Unpaired Restoration of Images and Point Clouds'' was accepted by IEEE TPAMI.
  • [04/2024] Our paper ''A Systematic Survey of Deep Learning-based Single-Image Super-Resolution'' was accepted by ACM Computing Surveys.
  • [03/2024] Two papers (DictSR and LoS) were accepted by CVPR 2024.
  • [03/2024] Our paper ''Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis'' was accepted by IEEE TIP.
  • [01/2024] One paper (ACRF) was accepted by ICLR 2024.
  • [08/2023] Our paper ''3D Face Recognition: Two Decades of Progress and Prospects'' was accepted by ACM Computing Surveys.
  • [07/2023] Our paper ''Lightweight Pixel Difference Networks for Efficient Visual Representation Learning'' was accepted by IEEE TPAMI.
  • [07/2023] Five papers were accepted by ICCV 2023.
  • [02/2023] One paper (PointCMP) was accepted by CVPR 2023.
  • [01/2023] We are organizing NTIRE Stereo Image SR Challenge and NTIRE Light Field Image SR Challenge @ CVPR 2023.
  • [12/2022] We are organizing a Special Issue "Advanced Image Restoration and Enhancement in the Wild" on IET Computer Vision.
  • [07/2022] Our paper ''Dense Nested Attention Network for Infrared Small Target Detection'' was accepted by IEEE TIP.
  • [07/2022] Our paper ''Exploring Fine-Grained Sparsity in CNNs for Efficient Inference'' was accepted by IEEE TPAMI.
  • [07/2022] One paper (MMSR) was accepted by ECCV 2022.
  • [04/2022] One paper (IF-ConvTransformer) was accepted by UbiComp 2022.
  • [03/2022] Three papers (LLT, PoSFeat, OACC-Net) were accepted by CVPR 2022.
  • [02/2022] Our paper ''Disentangling Light Fields for Super-Resolution and Disparity Estimation'' was accepted by IEEE TPAMI.
  • [01/2022] We are organizing NTIRE Stereo Image Super-Resolution Challenge @ CVPR 2022.
  • [07/2021] One paper (ArbSR) was accepted by ICCV 2021.
  • [03/2021] Two papers (DASR, SMSR) were accepted by CVPR 2021.

    		•
    Publications

    		Unsupervised Degradation Representation Learning for Unpaired Restoration of Images and Point Clouds

    Longguang Wang, Yulan Guo*, Yingqian Wang, Xiaoyu Dong, Qingyu Xu, Jungang Yang, Wei An

    TPAMI, 2024

    [Paper] [Code]


    		Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution

    Longguang Wang, Juncheng Li, Yingqian Wang, Qingyong Hu, Yulan Guo*

    CVPR, 2024

    [Paper] [Code]


    		Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution

    Zhengyu Liang, Yingqian Wang, Longguang Wang, Jungang Yang*, Shilin Zhou, Yulan Guo,

    ICCV, 2023

    [Paper] [Code]


    		Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

    Xiaoyu Dong, Naoto Yokoya*, Longguang Wang, Tatsumi Uezato

    ECCV, 2022

    [Paper] [Code]


    		Occlusion-Aware Cost Constructor for Light Field Depth Estimation

    Yingqian Wang, Longguang Wang, Zhengyu Liang, Jungang Yang*, Wei An, Yulan Guo

    CVPR, 2022

    [Paper] [Code]


    		Disentangling Light Fields for Super-Resolution and Disparity Estimation

    Yingqian Wang, Longguang Wang, Gaochang Wu, Jungang Yang*, Wei An, Jingyi Yu, Yulan Guo

    IEEE TPAMI, 2022

    [Paper] [Project]


    		Learning A Single Network for Scale-Arbitrary Super-Resolution

    Longguang Wang, Yingqian Wang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo*

    ICCV, 2021

    [Project], [Demo], [Paper], [Code], [News]


    		Unsupervised Degradation Representation Learning for Blind Super-Resolution

    Longguang Wang, Yingqian Wang, Xiaoyu Dong, Qingyu Xu, Jungang Yang, Wei An, Yulan Guo*

    CVPR, 2021

    [Paper], [Code], [News], [Video]


    		Exploring Sparsity in Image Super-Resolution for Efficient Inference

    Longguang Wang, Xiaoyu Dong, Yingqian Wang, Xinyi Ying, Zaiping Lin, Wei An, Yulan Guo*

    CVPR, 2021

    [Paper], [Code], [News], [Video]


    		Light Field Image Super-Resolution Using Deformable Convolution

    Yingqian Wang, Jungang Yang*, Longguang Wang, Xinyi Ying, Tianhao Wu, Wei An, Yulan Guo

    IEEE TIP, 2021

    [Paper], [Code]


    		Spatial-Angular Interaction for Light Field Image Super-Resolution

    Yingqian Wang, Longguang Wang, Jungang Yang*, Wei An, Jingyi Yu, Yulan Guo

    ECCV, 2020

    [Paper], [Code], [News]


    		Parallax Attention for Unsupervised Stereo Correspondence Learning

    Longguang Wang, Yulan Guo*, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An

    IEEE TPAMI, 2020

    [Paper], [Code], [News(三维视觉), (深蓝)], [Video]


    		Deep Video Super-Resolution Using HR Optical Flow Estimation

    Longguang Wang, Yulan Guo*, Li Liu, Zaiping Lin, Xinpu Deng, Wei An

    IEEE TIP, 2020

    [Paper], [Code], [News]


    		DeOccNet: Learning to See Through Foreground Occlusions in Light Fields

    Yingqian Wang, Tianhao Wu, Jungang Yang*, Longguang Wang, Wei An, Yulan Guo

    WACV, 2020

    [Paper], [Code]


    		Learning Parallax Attention for Stereo Image Super-Resolution

    Longguang Wang, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo*

    CVPR, 2019

    [Paper], [Code], [News], [Video]


    		Flickr1024: A Large-Scale Dataset for Stereo Image Super-Resolution

    Yingqian Wang, Longguang Wang, Jungang Yang, Wei An, Yulan Guo

    ICCVW, 2019

    [Paper], [Project]


    		Learning for Video Super-Resolution through HR Optical Flow Estimation

    Longguang Wang, Yulan Guo*, Zaiping Lin, Xinpu Deng, Wei An

    ACCV, 2018

    [Paper], [Code]


    		VideoDirector: Precise Video Editing via Text-to-Video Models

    Yukun Wang, Longguang Wang, Zhiyuan Ma, Qibin Hu, Kai Xu, Yulan Guo*

    arXiv

    [Paper] [Code]


    		Unsupervised Degradation Representation Learning for Unpaired Restoration of Images and Point Clouds

    Longguang Wang, Yulan Guo*, Yingqian Wang, Xiaoyu Dong, Qingyu Xu, Jungang Yang, Wei An

    TPAMI, 2024

    [Paper] [Code]


    		AEDNet: Adaptive Embedding and Multiview-Aware Disentanglement for Point Cloud Completion

    Zhiheng Fu, Longguang Wang, Lian Xu, Yulan Guo, Zhiyong Wang, Hamid Laga, Yulan Guo, Farid Boussaid, Mohammed Bennamoun*

    ECCV, 2024

    [Paper] [Code]


    		VAPCNet: Viewpoint-Aware 3D Point Cloud Completion

    Zhiheng Fu, Longguang Wang, Lian Xu, Yulan Guo, Hamid Laga, Zhiyong Wang, Farid Boussaid, Mohammed Bennamoun*

    ICCV, 2023

    [Paper] [Code]


    		Distractor-Free Novel View Synthesis via Exploiting Memorization Effect in Optimization

    Yukun Wang, Kunhong Li, Minglin Chen, Longguang Wang, Shunbo Zhou, Kaiwen Xue, Yulan Guo*

    ECCV, 2024

    [Paper] [Code]


    		Tangram-Splatting: Optimizing 3D Gaussian Splatting Through Tangram-inspired Shape Priors

    Yi Wang, Ningze Zhong, Minglin Chen, Longguang Wang, Yulan Guo*

    ACM MM, 2024

    [Paper] [Code]


    		Learning Spherical Radiance Field for Efficient 360° Unbounded Novel View Synthesis

    Minglin Chen, Longguang Wang, Yinjie Lei, Zilong Dong, Yulan Guo*

    IEEE TIP, 2024

    [Paper], [Code],


    		AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers

    Runqing Jiang, Ye Zhang, Longguang Wang, Pengpeng Yu, Yulan Guo*

    AAAI 2025

    [Paper] [Code]


    		ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression

    Guangchi Fang, Qingyong Hu, Longguang Wang, Yulan Guo*

    ICLR 2024

    [Paper] [Code]


    		Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

    Zhuo Su, Jiehua Zhang, Longguang Wang, Hua Zhang, Zhen Liu, Matti Pietikäinen, Li Liu*

    IEEE TPAMI, 2023

    [Paper] [Code]


    		Exploring Fine-Grained Sparsity in Convolutional Neural Networks for Efficient Inference

    Longguang Wang, Yulan Guo*, Xiaoyu Dong, Yingqian Wang, Xinyi Ying, Zaiping Lin, Wei An

    IEEE TPAMI, 2022

    [Paper] [Code]


    		Learnable Lookup Table for Neural Network Quantization

    Longguang Wang, Xiaoyu Dong, Yingqian Wang, Li Liu, Wei An, Yulan Guo*

    CVPR, 2022

    [Paper] [Code]


    		Learning Representations from Foundation Models for Domain Generalized Stereo Matching

    Yongjian Zhang, Longguang Wang, Kunhong Li, Yun Wang, Yulan Guo*

    ECCV, 2024

    [Paper] [Code]


    		LoS: Local Structure-Guided Stereo Matching

    Kunhong Li, Longguang Wang, Ye Zhang, Kaiwen Xue, Shunbo Zhou, Yulan Guo*

    CVPR, 2024

    [Paper] [Code]


    		Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos

    Zhiqiang Shen, Xiaoxiao Sheng, Hehe Fan, Longguang Wang, Yulan Guo, Qiong Liu, Hao Wen, Xi Zhou

    ICCV, 2023

    [Paper] [Code]


    		Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos

    Xiaoxiao Sheng, Zhiqiang Shen, Gang Xiao, Longguang Wang, Yulan Guo, Hehe Fan

    ICCV, 2023

    [Paper] [Code]


    		Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection

    Boyang Li, Yingqian Wang, Longguang Wang, Fei Zhang, Ting Liu, Zaiping Lin, Wei An, Yulan Guo*,

    ICCV, 2023

    [Paper] [Project] [Code]


    		PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos

    Zhiqiang Shen, Xiaoxiao Sheng, Longguang Wang*, Yulan Guo, Qiong Liu, Xi Zhou

    CVPR, 2023

    [Paper] [Code]


    		Dense Nested Attention Network for Infrared Small Target Detection

    Boyang Li, Chao Xiao, Longguang Wang, Yingqian Wang, Zaiping Lin, Miao Li, Wei An, Yulan Guo

    IEEE TIP, 2022

    [Paper] [Code]


    		IF-ConvTransformer: A Framework for Human Activity Recognition Using IMU Fusion and ConvTransformer

    Ye Zhang, Longguang Wang, Huiling Chen, Aosheng Tian, Shilin Zhou, Yulan Guo

    UbiComp, 2022

    [Paper] [Code]


    		Decoupling Makes Weakly Supervised Local Feature Better

    Kunhong Li, Longguang Wang, Li Liu, Qing Ran, Kai Xu, Yulan Guo*

    CVPR, 2022

    [Paper] [Code]


    Challenges & Workshops
    		NTIRE 2024 Challenge on Stereo Image SR @ CVPR 2024

    Longguang Wang, Yulan Guo, Yingqian Wang, Juncheng Li, Zhi Jin, Shuhang Gu, Radu Timofte

    [Webpage] [Project]


    		NTIRE 2024 Challenge on Light Field Image SR @ CVPR 2024

    Yingqian Wang, Longguang Wang, Zhengyu Liang, Jungang Yang, Yulan Guo, Radu Timofte

    [Webpage] [Project]


    		NTIRE 2023 Challenge on Stereo Image SR @ CVPR 2023

    Longguang Wang, Yulan Guo, Yingqian Wang, Juncheng Li, Shuhang Gu, Radu Timofte

    [Webpage] [Project] [Challenge Paper]


    		NTIRE 2023 Challenge on Light Field Image SR @ CVPR 2023

    Yingqian Wang, Longguang Wang, Zhengyu Liang, Jungang Yang, Radu Timofte, Yulan Guo

    [Webpage] [Project] [Challenge Paper]


    		NTIRE 2022 Challenge on Stereo Image SR @ CVPR 2022

    Longguang Wang, Yulan Guo, Yingqian Wang, Juncheng Li, Shuhang Gu, Radu Timofte

    [Webpage] [Project] [Challenge Paper]