信息与通信工程学院
|
|
|
|
导师代码: |
11983
|
导师姓名: |
刘帅成
|
性 别: |
男 |
特 称: |
四川省特聘专家
|
职 称: |
教授
|
学 位: |
工学博士学位
|
属 性: |
专职 |
电子邮件: |
liushuaicheng@uestc.edu.cn
|
|
|
学术经历:
|
|
2011年1月-2014年12月,新加坡国立大学,博士;
2008年9月-2010年12月,新加坡国立大学,硕士;
2004年9月-2008年6月,四川大学,学士。
工作经历:
2023年5月-至今,电子科技大学, 信息与通信工程学院,教授;
2018年1月-2023年5月,电子科技大学, 信息与通信工程学院,副教授;
2015年3月-2017年12月,电子科技大学, 电子工程学院,副教授;
2014年10月至今,电子科技大学图像处理研究所;
2013年5月-8月,美国西雅图,Adobe创新技术实验室;
2012年2月-5月,微软亚洲研究院计算机视觉组。
|
|
个人简介:
|
|
个人主页:
http://www.liushuaicheng.org/
长期从事计算机底层视觉(Low-level vision), 计算摄影学(Computational photography) 方面研究,发表顶会(CVPR, ICCV, ECCV, AAAI, SIGGRAPH, SIGGRAPH Asia)50多篇,期刊(TPAMI, IJCV, TOG, TNNLS, TIP, TCSVT, TMM)30多篇,共被引5000余次(google scholar, 截止2024年3月),获4项国际竞赛冠军,部分研究成果编入美国哥伦比亚大学计算机视觉课程。研究成果应用于手机超画质,涵盖“华为、小米、Oppo、Vivo”等多个主流品牌。获校学术新人奖,入选四川省特聘专家。
|
|
科研项目:
|
|
《面向复杂场景和相机自由运动的在线视频防抖研究》,国家自然科学基金,面上项目,主持,2024-2027
《图像视频智能协同处理》,四川省自然科学基金,创新研究群体项目,参与,2023-2026
《图像超分辨率关键技术研究》,四川省自然科学基金,面上项目,主持,2023-2025
《基于视频编码的计算摄像学研究》,国家自然科学基金,面上项目,主持,2019-2022
《视频防抖关键技术研究》,国家自然科学基金,青年项目,主持,2016-2018
《电子内镜和无线胶囊内镜图像处理关键技术研究》,国家自然科学基金,国际(地区)合作与交流项目, 参与,2018-2022
《图像稳像算法技术研究》,华为科技有限公司,主持,2016-2017.
《基于视频编码的计算机视觉关键技术研究》,四川省国际合作交流项目,主持,2019-2021
|
|
研究成果:
|
|
Recent Publications(2020~):
Conferences:
[1] A. Luo, X. Li, F. Yang, J. Liu, H. Fan, S. Liu, "FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[2] X. Luo, A. Luo, Z. Wang, C. Lin, B. Zeng, S. Liu, "Efficient Meshflow and Optical Flow Estimation from Event Cameras", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[3] T. Zhou, H. Li, Z. Wang, A. Luo, C. Zhang, J. Li, B. Zeng, S. Liu, "Rectangling for Image Stitching with Diffusion Models", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[4] H. Xu, H. Li, Y. Wang, S. Liu, C.-W. Fu, "HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[5] H. Jiang, A. Luo, H. Fan, S. Han, S. Liu, "Low-Light Image Enhancement with Wavelet-based Diffusion Models",ACM Transactions on Graphics, in Proc. SIGGRAPH Asia, 2023
[6] W. Yan, R. Tan, B. Zeng, S. Liu, "Deep Homography Mixture for Single Image Rolling Shutter Correction", International Conference on Computer Vision (ICCV), 2023
[7] Z. Zhang, Z. Liu, P. Tan, B. Zeng, S. Liu, "Minimum Latency Deep Online Video Stabilization", International Conference on Computer Vision (ICCV), 2023
[8] H. Jiang, H. Li, S. Han, H. Fan, B. Zeng, S. Liu, "RealHomo: Supervised Homography Learning with Realistic Dataset Generation", International Conference on Computer Vision (ICCV), 2023
[9] T. Jiang, C. Wang, X. Li, R. Li, H. Fan, S. Liu, "MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion", International Conference on Computer Vision (ICCV), 2023
[10] X. Luo, K. Luo, A. Luo, Z. Wang, P. Tan, S. Liu, "Learning Optical Flow from Event Camera with Rendered Dataset", International Conference on Computer Vision (ICCV), 2023
[11] S. Chen, H. Xu, R. Li, G. Liu, C. Fu, S. Liu, "SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration", International Conference on Computer Vision (ICCV), 2023
[12] L. Nie,C. Lin,K. Liao,S. Liu,Y. Zhao “Parallax-Tolerant Unsupervised Deep Image Stitching”, International Conference on Computer Vision (ICCV), 2023
[13] Y. Wang,Z. Liu,J. Liu,S. Xu,S. Liu,“Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network”, International Conference on Computer Vision (ICCV), 2023
[14] C. Deng,A. Luo,H. Huang,S. Ma,J. Liu,S. Liu,“Explicit Motion Disentangling for Efficient Optical Flow Estimation”, International Conference on Computer Vision (ICCV), 2023
[15] A. Luo, F. Yang, X. Li, L. Nie, C. Lin, H. Fan, S. Liu, GAFlow: Incorporating Gaussian Attention into Optical Flow, International Conference on Computer Vision (ICCV), 2023
[16] G. Wu,W. Wang,K. Luo,X. Liu,Q. Zheng,S. Liu,X. Jiang,G. Zhai,X. Liu,"AccFlow: Backward Accumulation for Long-Range Optical Flow", International Conference on Computer Vision (ICCV), 2023
[17] J. Jing, J. Li, P. Xiong, J. Liu, S. Liu, Y. Guo, X. Deng, M. Xu, L. Jiang, L. Sigal, "Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching", International Conference on Computer Vision (ICCV), 2023
[18] L. Yu, X. Li, Y. Li, T. Jiang, Q. Wu, H. Fan, S. Liu, "DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution", IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), NTIRE Challenges - Efficient SR (Winner) , 2023
[19] H. Jiang, H. Li, Y. Lu, S. Han, S. Liu, "Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint", Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023.
[20] Y. Li, H. Huang, L. Jia, H. Fan, S. Liu, "D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution", European Conference on Computer Vision (ECCV). 2022.
[21] Z. Liu, Y. Wang, B. Zeng, S. Liu, "Ghost-free High Dynamic Range Imaging with Context-aware Transformer", European Conference on Computer Vision (ECCV). 2022.
[22] Y. Han, K. Luo, A. Luo, J. Liu, H. Fan, G. Luo, S. Liu, "RealFlow: EM-based Realistic Optical Flow Datasets Generation from Videos", European Conference on Computer Vision (ECCV). 2022. (Oral Presentation)
[23] Z. Luo, Y. Li, S. Cheng, L. Yu, Z. Wen, H. Fan, J. Sun, S. Liu, "BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment", IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), NTIRE Challenges - SR (Winner) , 2022
[24] A. Luo, F. Yang, X. Li, S. Liu, "Learning Optical Flow with Kernel Patch Attention", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[25] M. Hong, Y. Lu, N. Ye, C. Lin, Q. Zhao, S. Liu, "Unsupervised Homography Estimation with Coplanarity-Aware GAN", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[26] C. Tang, Y. Yang, B. Zeng, P. Tan, S. Liu, "Learning to Zoom Inside Camera Imaging Pipeline", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[27] F. Zhu, S. Zhao, P. Wang, H. Wang, H. Yan, S. Liu, "Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[28] L. Nie, C. Lin, K. Liao, S. Liu, Y. Zhao, "Deep Rectangling for Image Stitching: A Learning Baseline", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Oral Presentation)
[29] H. Li, Z. Cui, S. Liu, P. Tan, "RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[30] Z. Luo, H. Huang, L. Yu, Y. Li, H. Fan, S. Liu, "Deep Constrained Least Squares for Blind Image Super-Resolution", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[31] L. Yang, R. Shrestha, W. Li, S. Liu, G. Zhang, Z. Cui, P. Tan,"SceneSqueezer: Learning to Compress Scene for Camera Relocalization", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Oral Presentation)
[32] J. Li, P. Wang, T. Cai, Z. Yan, P. Xiong, J. Liu, L. Yang, H. Fan, S. Liu, "Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022. (Oral Presentation)
[33] H. Xu, N. Ye, G. Liu, B. Zeng, S. Liu, "FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration", Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022.
[34] A. Luo, F. Fang, K. Luo, X. Li, H. Fan, S. Liu, "Learning Optical Flow with Adaptive Graph Reasoning", Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022.
[35] N. Ye, C. Wang, H. Fan, S. Liu, "Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection", International Conference on Computer Vision (ICCV), 2021. (Oral Presentation)
[36] C. Zhang, Y. Zhang, C. Chen, S. Liu, B. Zeng, H. Bao, Z. Cui, "DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization", International Conference on Computer Vision (ICCV), 2021. (Oral Presentation)
[37] H. Xu, S. Liu, G. Wang, G. Liu, B. Zeng, "OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration", International Conference on Computer Vision (ICCV), 2021.
[38] H. Li, K. Luo, S. Liu, "GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning", International Conference on Computer Vision (ICCV), 2021.
[39] Y. Yang, Y. Xiang, S. Liu, L. Wu, B. Zhao, B. Zeng, "GLM-Net : Global and Local Motion Estimation via Task-Oriented Encoder-Decoder Structure", ACM Multimedia (MM), 2021.
[40] Z. Liu, W. Lin, X. Li, Q. Rao, T. Jiang, M. Han, H. Fan, S. Liu, "ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging" , IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), NTIRE Challenges - HDR (Winner) , 2021
[41] Z. Luo, L. Yu, X. Mo, Y. Li, L. Jia, J. Sun, S Liu,"EBSR: Feature Enhanced Burst Super-Resolution with Deformable Alignment", IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), NTIRE Challenges - SR (Winner), 2021
[42] S. Cheng, X. Lu, Y. Zhou, X. Zhang, H. Fan, J. Sun, S Liu,"Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report", IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), MAI Challenges - Smartphone Image Denoising (Runner up), 2021
[43] K. Luo, C. Wang, S. Liu, H. Fan, J. Wang, J. Sun, "UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[44] S. Cheng, Y. Wang, H. Huang, D. Liu, H. Fan, S. Liu,"NBNet: Noise Basis Learning for Image Denoising with Subspace Projection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[45] C. Zhang, Z. Cui, Y. Zhang, B. Zeng, M. Pollefeys, S. Liu,"Holistic 3D Scene Understanding from a Single Image with Implicit Representation ", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[46] J. Tan, S. Zhao, P. Xiong, J. Liu, H. Fan, S. Liu,"Practical Wide-Angle Portraits Correction with Deep Structured Models", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[47] J. Zhang, C. Wang, S. Liu, L. Jia, J. Wang, J. Zhou, J. Sun,"Content-Aware Unsupervised Deep Homography Estimation", European Conference on Computer Vision (ECCV). 2020 (Oral Presentation)
[48] M. Zhou, J. Wu, Y. Liu, S. Liu, C. Zhu, "DaST: Data-free Substitute Training for Adversarial Attacks", IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2020. (Oral Presentation)
[49] P. Dai, Y. Zhang, Z. Li, S. Liu, B. Zeng, "Neural Point Cloud Rendering via Multi-Plane Projection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
Journal:
[1] H. Li, H. Jiang, A. Luo, P. Tan, H. Fan, B. Zeng, S. Liu, "DMHomo: Learning Homography with Diffusion Models", ACM Transactions on Graphics (present at SIGGRAPH), 2024.
[2] H. Li, K. Luo, B. Zeng, S. Liu, "GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning", International Journal of Computer Vision (IJCV), 2024.
[3] H. Li, D. Liu, Y. Zeng, S. Liu, T. Gan, N. Rao, J. Yang, B. Zeng, "Single-Image-Based Deep Learning for Segmentation of Early Esophageal Cancer Lesions", IEEE Transactions on Image Processing (TIP), 2024.
[4] R. Li, P. Dai, G. Liu, S. Zhang, B. Zeng, S. Liu, "PBR-GAN: Imitating Physically Based Rendering with Generative Adversarial Networks", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 34, no. 3, pp. 1827-1840, 2024.
[5] S. Liu, Y. Lu, H. Jiang, N. Ye, C. Wang, B. Zeng, "Unsupervised Global and Local Homography Estimation with Motion Basis Learning", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 6, pp. 7885-7899, 2023.
[6] S. Liu, N. Ye, C. Wang, J. Zhang, L. Jia, K. Luo, J. Wang, J. Sun,"Content-Aware Unsupervised Deep Homography Estimation and Its Extensions", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 45, no. 3, pp. 2849-2863, 2023.
[7] Q. He, Z. Wang, H. Zeng, Y. Zeng, Y. Liu, S. Liu, B. Zeng, “Stereo RGB and Deeper LIDAR-Based Network for 3D Object Detection in Autonomous Driving”, IEEE Transactions on Intelligent Transportation System (TITS), vol. 24, no. 1, pp. 152-162, 2023.
[8] L. Nie, C. Lin, K. Liao, S. Liu, Y. Zhao, “Deep Rotation Correction without Angle Prior”, IEEE Transactions on Image Processing (TIP), vol. 32, pp. 2879-2888, 2023.
[9] R. Li, C. Wang, J. Wang, G. Liu, H. Zhang, B. Zeng, S. Liu, "UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 32, no. 11, pp. 7532-7456, 2022.
[10] S. Liu, K. Luo, N. Ye, C. Wang, J. Wang, B. Zeng, "OIFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning", IEEE Transactions on Image Processing (TIP), vol. 30, pp. 6420-6433, 2021.
[11] L. Nie, C. Lin, K. Liao, S. Liu, Y. Zhao, "Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images", IEEE Transactions on Image Processing (TIP), vol. 30, pp. 6184-6197, 2021.
[12] J. Qiu, C. Chen, S. Liu, H. Zhang, B. Zeng, "SlimConv: Reducing Channel Redundancy in Convolutional Neural Networks by Features Recombining", IEEE Transactions on Image Processing (TIP), vol. 30, pp. 6434-6445, 2021.
[13] C. Wang, S. Zhao, L. Zhu, K. Luo, Y. Guo, J. Wang, S. Liu, "Semi-supervised Pixel-level Scene Text Segmentation by Mutually Guided Network", IEEE Transactions on Image Processing (TIP), vol. 30, pp. 8212-8221, 2021.
[14] R. Li, S. Liu, G. Wang, G. Liu, B. Zeng, "JigsawGAN: Auxiliary Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks", IEEE Transactions on Image Processing (TIP), 2021.
[15] T. Sun, G. Liu, R. Li, S. Liu, S. Zhu, B. Zeng, "Quadratic Terms based Point-to-Surface 3D Representation for Deep Learning of Point Cloud", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
[16] S. Liu, H. Li, Z. Wang, J. Wang, S. Zhu, B. Zeng, "DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
[17] S. Liu, K. Luo, A. Luo, C. Wang, F. Meng, B. Zeng, "ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
[18] L. Nie, C. Lin, K. Liao, S. Liu, Y. Zhao, "Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
[19] P. Dai, Z. Li, Y. Zhang, S. Liu, B. Zeng, "PBR-Net: Imitating Physically Based Rendering using Deep Neural Network", IEEE Transactions on Image Processing (TIP), vol. 29, pp. 5980-5992, 2020.
[20] R. Li, C. Wu, S. Liu, J. Wang, G. Wang, G. Liu, B. Zeng, "SDP-GAN: Saliency Detail Preservation Generative Adversarial Networks for High Perceptual Quality Style Transfer", IEEE Transactions on Image Processing (TIP), vol. 30, pp. 374-385, 2020.
[21] L. Zhang, S. Liu, D. Liu, P. Zeng, X. Li, J. Song, L. Gao, "Rich Visual Knowledge-based Augmentation Network for Visual Question Answering", IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020
[22] Z. Wang, F. Zeng, S. Liu, B. Zeng, "OAENet: Oriented Attention Ensemble for Accurate Facial Expression Recognition", Pattern Recognition (PR), vol. 112, pp. 107694, 2020.
[23] R. Li, S. Liu, G. Liu, T. Sun, J. Guo, "Multi-exposure photomontage with hand-held cameras", Computer Vision and Image Understanding (CVIU), vol. 193, pp. 102929, 2020.
Recent Patents:
1.刘帅成;郑梓楠;陈才;章程,“一种基于运动友好的多对焦融合网络的图像融合方法”,电子科技大学,ZL202210396277.5,2023年12月26日
2.刘帅成;陈才;郑梓楠;章程,“一种基于可微几何传播的深度补全方法”,电子科技大学,ZL202210437598.5,2023年4月18日
3.刘帅成,叶年进,“一种基于内容感知的深度网格流鲁棒图像对齐方法”,电子科技大学,ZL202110498009.X,2022年3月15日
4.喻雷,万思琦,杨国强,刘帅成,“一种基于RAW图像的反光图像合成方法”,电子科技大学,ZL202110043430.1,2022年7月22日
5.刘帅成,张星迪,何志伟,“一种高动态范围图片的合成方法”,电子科技大学,ZL201810488694.6, 2022年3月4日
6.刘帅成,彭凌冰,何志伟,曾兵,“一种基于合成的内窥镜视频去模糊方法”,ZL201710993832.1,电子科技大学,2021年6月29日
7.刘帅成,李茹,刘光辉,“一种基于MRF区域选择的多曝光图像融合方法”,ZL201711354103.8,电子科技大学,2021年6月1日
8.刘帅成,杨涛涛,孙超,曾兵,“一种基于双目立体视觉系统的前景分割方法”,ZL201710848174.7,电子科技大学,2020年7月28日
9.刘帅成,谢德华,曾兵,“一种双目图像的本征性质分解方法”,电子科技大学,ZL201910288161.8,电子科技大学,2019年12月17日
|
|
专业研究方向:
|
专业名称 |
研究方向 |
招生类别 |
081000信息与通信工程 |
06图像与视频处理,09机器学习与人工智能,10信号与信息智能处理 |
硕士学术学位 |
|
|
|
|
|