Xidian University logo
CVIA · 空天工业机器视觉组
Computer Vision for Industry and Aerospace · XDU
CNEN
Faculty Profile

宋锐 · Rui Song

教授，博士生导师，长期围绕三维空间智能、三维定位与测量、6D 位姿估计以及工程视觉系统开展研究与应用。

宋锐 · Rui Song
教授 · 博士生导师

西安电子科技大学 · 通信工程学院 · ISN 国家实验室

图像传输与处理研究所

Email: rsong at xidian.edu.cn

Office: 科技楼 B-201 · Tel: +86(29)88202607

Mail: 陕西省西安市雁塔区太白南路 2 号，103# 信箱

Academic Profile

2003、2006、2009 年在西安电子科技大学分别获得学士、硕士和博士学位，2012 至 2013 年赴美国南加州大学开展访问研究。

ISN 国家实验室成员，图像传输与处理研究所成员，IEEE 会员，陕西省图象图形学会理事，CCF-CV 专委会委员，CSIG-3DV 专委会委员。IEEE T-PAMI、TNNLS、T-MM、T-CSVT、T-GRS、T-IP、Pattern Recognition、Remote Sensing 审稿人。

陕西高校青年创新团队负责人，陕西省“科学家+工程师”团队首席科学家。

曾获嫦娥五号先进个人、教育部科学技术进步奖一等奖、陕西省科学技术奖二等奖、测绘科学技术奖一等奖、中航工业集团科技进步奖二等奖、陕西省科技新星、西安电子科技大学华山学者菁英人才等荣誉。

主要研究方向为三维空间智能、计算机视觉中的三维定位与 6D 位姿估计，遥感影像智能处理。

研究坚持“问题从工程实践中提炼，成果在工程应用中检验”的理念，持续推进算法研究、硬件实现和系统部署的闭环验证。

教育背景西安电子科技大学本硕博 · USC 访问学者
近年发表近五年 SCI 论文 60 余篇，一作/通信 40 余篇
工程特色航天、航空、深海、工业智能中的机器视觉算法研究
研究方向三维空间智能、三维定位、目标 6D 位姿估计和跟踪
News
  • news icon【2026-03-06】祝贺CVIA组宋锐教授和郝丰达老师在中国航空工业集团第一飞机设计研究院人工智能“揭榜挂帅”大赛中荣膺“擂主”。
  • 【2026-03-06】2026 年博士仍有可用指标，欢迎对计算机视觉、图像分析、三维空间测量和 6D 位姿估计方向感兴趣的研究生邮件联系。
  • 【2026-02-27】2026 年硕士新增一个学硕指标，欢迎感兴趣的学子邮件咨询，工作时间通常可较快回复并安排线上交流。
  • 【2026-02-21】祝贺博士研究生刘志强 6D 位姿估计论文 “Exploring 6D Object Pose Estimation with Deformation” 被 CVPR 2026 录用。
  • 【2026-02-09】祝贺博士研究生荣琪单目深度估计论文 “Leveraging Spatiotemporal Cues for Self-Supervised Stereo Depth Estimation in Endoscopic Videos” 被 IEEE Transactions on Medical Imaging 录用。
  • 【2025-06-16】祝贺硕士研究生刘路远红外图像增强论文 “ASMF: A Self-Supervised Atmospheric Scatter Model-Based Fusion Network for Infrared Image Enhancement” 被 IEEE Transactions on Geoscience and Remote Sensing 录用。
  • 【2025-02-27】祝贺硕士研究生王庆元 6D 姿态估计论文 “SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow” 被 CVPR 2025 录用。

研究方向及成果

研究方向

主要研究方向为计算机视觉中的三维空间智能、三维定位与目标 6D 位姿估计。近年来围绕复杂空间目标几何感知、空间目标姿态估计、结构约束建模、点云理解和工程视觉系统部署形成连续研究积累，并兼顾图像/视频压缩与传输系统中的关键算法与架构实现。

近五年主持多项纵向科研项目，同时以横向课题形式主持十余项由航天科技集团、航空工业集团、中国科学院、中国兵器工业集团、中国电子科技集团等下属研究所委托的研发任务。近五年发表 SCI 论文 60 余篇，其中一作/通信作者论文 40 余篇，中科院二区以上论文 50 篇以上，并获多项国家发明专利。

Research Results & Applications

研究成果及应用

嫦娥五号核心压缩引擎

嫦娥五号核心压缩引擎

针对着陆器机械臂在月表操作视频的高保真对地传输，我们设计完成了上升器采样和分离监视多通道相机多模实时编码单元研制，该单元通过灵活的架构设计，实现了5路监视相机数据的不同分辨率、不同工作模式、不同压缩格式、不同解析需求的实时处理，将月表作业视频高效传输至中央电视台。

空间站天宫 / 天舟对接实时监视引导系统

空间站天宫 / 天舟对接实时监视引导系统

围绕空间站与货运飞船交会对接过程中的实时视频监视与引导需求，承担多路高清视频通信与图像处理系统研制，为空间站任务中的实时监视和地面分析提供稳定支撑。

万米深潜超高清视频压缩系统

万米深潜超高清视频压缩系统

面向马里亚纳海沟万米级海试实时直播任务，研制多通道影院级 4K 超高清视频编码系统及母船端解码系统，在深海复杂环境下稳定运行，为国家级直播任务提供了关键视频通信能力。

空间态势感知SSA中的目标位姿感知单元

空间态势感知 SSA 中的目标位姿感知单元

面向复杂空间目标的姿态感知与预警需求，构建基于目标检测、位姿估计与位姿跟踪的空间目标位姿实时智能感知单元，实现无人自主化空间态势预警。

空中硬式加油系统中的精准定位系统

空中硬式加油系统中的精准定位系统

围绕空中硬式加油过程中的精确定位需求，构建视觉感知、目标测量与运动引导一体化的定位系统方案，用于支持复杂飞行条件下的高精度相对位姿估计。

无人机监视影像的 2D-3D 配准及 DSM 实时投影

无人机监视影像的 2D-3D 配准及 DSM 实时投影

针对无人机监视成像与地理信息数据融合需求，开展了 2D–3D 配准与 DSM 实时投影关键技术研究。将旋翼无人机视场内的二维图像像素直接投影到三维 DSM 上，可用三维实时的方式监视前线动态，提升目标观测、定位与态势理解能力。

Algorithm Competitions

竞赛获奖

一飞院揭榜挂帅擂主

2026 · 中航一飞院人工智能“揭榜挂帅”大赛“擂主”

2026年4月10日，中国航空工业集团第一飞机设计研究院（简称“一飞院”）人工智能“揭榜挂帅”大赛决赛及颁奖仪式在西安阎良圆满落幕。在这场代表国内航空AI领域顶尖水平的技术比拼中，CVIA组宋锐教授与郝丰达老师带领的团队在航空硬式加油6D位姿估计算法竞赛中，在精度、稳定性、效率等方面均取得优异成绩，勇夺全场最高荣誉“擂主”，李娇娇教授领衔的团队斩获一等奖，充分彰显了CVIA组在航空视觉与智能定位领域的硬核积淀。

相关链接：https://mp.weixin.qq.com/s/2VfPGwEh0p6J40OQTSVSIA

相关链接：https://news.xidian.edu.cn/info/2106/295826.htm

相关链接：https://mp.weixin.qq.com/s/uE817SGZy7xe2fgFPPbXuQ

2023 ICCV BOP Challenge 单模型赛道冠军

2023 · ICCV BOP Challenge 单模型赛道冠军

由西安电子科技大学、EPFL 和 Magic Leap 组成的联合队伍获得 BOP Challenge 单模型赛道冠军，并受邀在 R6D workshop 上汇报。获奖方法采用检测、估计、修正框架，在 RGB 与 RGB-D 设置下均显著领先。

2022 ECCV BOP Challenge 单模型赛道冠军

2022 · ECCV BOP Challenge 单模型赛道冠军

由西安电子科技大学、EPFL 和 Magic Leap 组成的联合队伍获得 BOP Challenge 单模型赛道冠军，并受邀在相关国际 workshop 上作报告。

2021 Completion3D Benchmark 第一名

2021 · Completion3D Benchmark 第一名

ASFM-Net 在斯坦福大学发布的 Completion3D leaderboard 上排名第一，是团队在点云补全方向的重要代表性成果。

2019 天智杯人工智能挑战赛科目一第二名

2019 · “天智杯”人工智能挑战赛科目一第二名

基于多视角卫星影像完成感兴趣区域的地物三维重建，体现了团队面向复杂工程任务的算法落地能力。

科研项目

Projects
  • 2025–2026：兵器工业集团 xx 所，xx 2D-3D 匹配算法研究。
  • 2023–2026：航天科技集团 xx 所，xx 目标姿态估计算法、数据集及管理软件。
  • 2023–2026：中航工业集团 xx 所，xx 加油视觉定位系统。
  • 2021–2023：中国航空工业集团公司 xx 飞机设计院，某 xx 型飞机机器视觉系统原型设计。
  • 2021–2023：中国科学院 xx 所，空间站 xx 目标姿态估计系统。
  • 2020–2021：中国科学院 xx 所，复杂空间目标三维重构技术研究。
  • 2019–2021：GF 重点实验室基金项目，xx 在轨数据影像实时处理算法及架构研究。
Systems
  • 2023–2025：中科院 xx 研究所，xx 卫星 TDI 相机压缩系统。
  • 2024–2026：中科院 xx 研究所，xx 卫星监视相机图像处理器。
  • 2022–2025：中科院 xx 研究所，xx 相机在轨高集成度压缩系统。
  • 2022–2023：xx 研究院，DSC 视频压缩解压缩 IP 原型设计。
  • 2022–2024：深圳 xx 公司，PNG 图像解码 IP 设计。
  • 2021–2023：兵器工业集团 xx 所，某装备 xx 全景实景实时生成系统。
  • 2020–2022：中科院 xx 研究所，某在轨压缩项目。
  • 2019–2021：中科院 xx 研究所，深海超高清（4096×2160@60fps）视频编解码系统研制。
  • 2019–2020：中科院 xx 研究所，超高分辨率（5000×5000@5fps）多模相机压缩软件研制。
  • 2020–2022：中科院 xx 研究所，xx 探测卫星超高清（8000×6000@5fps）混合模式压缩软件研制。
  • 2012–2017：航天五院，xx 摄像机视频编码、解码系统研制（天舟一号，2017 年 4 月发射成功，任务完成）。
  • 2014–2017：航天八院，摄像机地面测试设备。
  • 2015–2017：航天五院，试验测试电路的研制（嫦娥五号）。
  • 2014–2016：航天五院，空间应用多路高清视频通信系统（嫦娥五号，预计 2017 年发射）。
  • 2011–2015：中航工业集团，H.264/AVC 视频编解码芯片 IP 研发。

论文成果

Selected Publications & Output
Exploring 6D Object Pose Estimation with Deformation

Exploring 6D Object Pose Estimation with Deformation

Zhiqiang Liu, Rui Song, Jiaojiao Li, Yinlin Hu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

This paper introduces deformation modeling for 6D pose estimation under non-rigid deformation and heavy occlusion, improving robustness and estimation accuracy while preserving geometric consistency.

[Paper][Project][Code]
SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow

SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow

Qingyuan Wang, Rui Song, Jiaojiao Li, Kerui Cheng, David Ferstl, Yinlin Hu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

We propose a plug-and-play pose refinement algorithm that injects shape-constrained scene flow into the optimization loop, improving both estimation accuracy and scene adaptability from an existing initial pose.

[Paper][Project][Code]
Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

Yang Hai, Rui Song, Jiaojiao Li, David Ferstl, Yinlin Hu
IEEE/CVF International Conference on Computer Vision (ICCV), 2023

This work presents a self-supervised 6D pose-estimation framework without depth or additional annotations, and improves real-scene generalization and refinement via pseudo-flow supervision derived from multi-view geometric consistency.

[Paper][Project][Code]
Shape-Constraint Recurrent Flow for 6D Object Pose Estimation

Shape-Constraint Recurrent Flow for 6D Object Pose Estimation

Yang Hai, Rui Song, Jiaojiao Li, Yinlin Hu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

The paper proposes a shape-constrained recurrent-flow framework that implicitly embeds 3D object shape into iterative matching and pose solving for more efficient and accurate 6D pose refinement.

[Paper][Project][Code]
Rigidity-Aware Detection for 6D Object Pose Estimation

Rigidity-Aware Detection for 6D Object Pose Estimation

Yang Hai, Rui Song, Jiaojiao Li, Mathieu Salzmann, Yinlin Hu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

For 6D pose estimation under complex occlusion, the paper proposes a rigidity-aware detection strategy that uses visibility-guided sampling to obtain more stable detection initialization.

[Paper][Project][Code]
Structure-Aware Graph Convolution Network for Point Cloud Parsing

Structure-Aware Graph Convolution Network for Point Cloud Parsing

Fengda Hao, Jiaojiao Li, Rui Song, Yunsong Li, Kailang Cao
IEEE Transactions on Multimedia, 2023

This work proposes SA-GCN, a structure-aware graph convolution network with adaptive dilated KNN, learnable graph filters, and structure-aware feature transformation for point-cloud classification and segmentation.

HE2LM-AD: Hierarchical and Efficient Attitude Determination Framework with Adaptive Error Compensation Module Based on ELM Network

HE2LM-AD: Hierarchical and Efficient Attitude Determination Framework with Adaptive Error Compensation Module Based on ELM Network

Kailang Cao, Jiaojiao Li, Rui Song, Yunsong Li
ISPRS Journal of Photogrammetry and Remote Sensing, 2023

For remote-sensing satellite attitude determination, the paper proposes an efficient hierarchical framework combining adaptive EKF, ELM-based error compensation, and weighted smoothing to improve high-precision attitude estimation.

Lightweight Centroid Locating Method for the Satellite Target

Lightweight Centroid Locating Method for the Satellite Target

Luyuan Liu, Luyao Han, Jiaojiao Li, Hui Xia, Peng Rao, Rui Song
Journal of Xidian University, 2023

For onboard processors with limited computational capability, the paper proposes an ultra-lightweight satellite centroid localization method based on line and contour features, enabling accurate and real-time localization at low cost.

Mixed Feature Prediction on Boundary Learning for Point Cloud Semantic Segmentation

Mixed Feature Prediction on Boundary Learning for Point Cloud Semantic Segmentation

Fengda Hao, Jiaojiao Li, Rui Song, Yunsong Li, Kailang Cao
Remote Sensing, 2022

This work proposes a boundary-aware self-supervised pretraining framework for point-cloud semantic segmentation, improving boundary-region and fine-structure segmentation quality.

Research on the On-orbit Real-time Space Target Detection Algorithm

Research on the On-orbit Real-time Space Target Detection Algorithm

Luyao Han, Chan Tan, Yunmeng Liu, Rui Song
Spacecraft Recovery & Remote Sensing, 2021

For real-time on-orbit detection of space targets against deep-space backgrounds, the paper proposes a target-detection algorithm based on morphological processing and inter-frame matching, validated on FPGA and DSP platforms.

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla
ACM International Conference on Multimedia (ACM MM), 2021

ASFM-Net improves point-cloud completion by learning prior knowledge in feature space through an asymmetrical Siamese feature-matching autoencoder.

Robust Interpolation of Correspondences for Large Displacement Optical Flow

Robust Interpolation of Correspondences for Large Displacement Optical Flow

Peng Zhang, Hui Xu, Rui Song, etc.
Pattern Recognition, 2017

A robust interpolation framework for large-displacement optical flow improves dense flow recovery from sparse but reliable correspondences.

Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow

Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow

Peng Zhang, Hui Xu, Rui Song, etc.
IEEE Transactions on Image Processing, 2016

This work develops an efficient coarse-to-fine PatchMatch strategy for large-displacement optical flow, balancing accuracy and efficiency.

全部论文列表

全部发表论文

以下条目按 IEEE Transactions 参考文献格式统一整理。部分论文目前仍为 early access / online ahead of print 状态，因此暂未包含正式卷期页码时，保留为在线优先发表信息。

计算机视觉、三维视觉、6D位姿估计

  1. R. Wang, R. Song, J. Zhang, and Y. Nie, "Leveraging Spatiotemporal Cues for Self-Supervised Stereo Depth Estimation in Endoscopic Videos," IEEE Trans. Med. Imaging, early access, Jan. 2026, doi: 10.1109/TMI.2026.3659145.
  2. Y. Sun, Y. Ma, Z. Chen, Z. Liu, B. Chen, and R. Song, "A Sliding Window for Data Reuse in Deep Convolution Operations to Reduce Bandwidth Requirements and Resource Utilization," Electronics, vol. 14, no. 3, art. 582, 2025.
  3. F. Hao, J. Li, R. Song, Y. Li, and K. Cao, "Structure-Aware Graph Convolution Network for Point Cloud Parsing," IEEE Trans. Multimed., vol. 25, pp. 7025–7036, 2023, doi: 10.1109/TMM.2022.3216951.
  4. Y. Hai, R. Song, J. Li, D. Ferstl, and Y. Hu, "Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023, pp. 14075–14085, doi: 10.1109/ICCV51070.2023.01294.
  5. Y. Hai, R. Song, J. Li, M. Salzmann, and Y. Hu, "Rigidity-Aware Detection for 6D Object Pose Estimation," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Vancouver, BC, Canada, 2023, pp. 8927–8936.
  6. Y. Hai, R. Song, J. Li, and Y. Hu, "Shape-Constraint Recurrent Flow for 6D Object Pose Estimation," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Vancouver, BC, Canada, 2023, pp. 4831–4840, doi: 10.1109/CVPR52729.2023.00468.
  7. F. Hao, J. Li, R. Song, Y. Li, and K. Cao, "Mixed Feature Prediction on Boundary Learning for Point Cloud Semantic Segmentation," Remote Sens., vol. 14, no. 19, p. 4757, Sep. 2022, doi: 10.3390/rs14194757.
  8. F. Hao, R. Song, J. Li, K. Cao, and Y. Li, "Cascaded Geometric Feature Modulation Network for Point Cloud Processing," Neurocomputing, vol. 492, pp. 474–487, Jul. 2022, doi: 10.1016/j.neucom.2022.04.007.
  9. Y. Xia, Y. Xia, W. Li, R. Song, K. Cao, and U. Stilla, "ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion," in Proc. 29th ACM Int. Conf. Multimedia, Oct. 2021, pp. 1938–1947, doi: 10.1145/3474085.3475348.
  10. B. Han, X. Jia, R. Song, F. Ran, and P. Rao, "Auto Complementary Exposure Control for High Dynamic Range Video Capturing," IEEE Access, vol. 9, pp. 144285–144299, 2021, doi: 10.1109/ACCESS.2021.3118416.
  11. 韩璐瑶, 谭婵, 刘云猛, and 宋锐, "在轨实时空间目标检测算法研究," 航天返回与遥感, vol. 42, no. 6, pp. 122–131, 2021, doi: 10.3969/j.issn.1009-8518.2021.06.012.
  12. S. Li and R. Song, "Bilateral Adaptive Quantization in HEVC," Multimed. Tools Appl., vol. 78, no. 2, pp. 2385–2399, 2019, doi: 10.1007/s11042-018-6312-y.
  13. R. Song, Y. Li, Y. Jia, Y. Wang, and P. Rao, "Efficient, Robust and Divisible Paired Comparison for Subjective Quality Assessment," Multimed. Tools Appl., vol. 77, no. 11, pp. 13597–13613, 2018, doi: 10.1007/s11042-017-4977-2.
  14. Y. Li, Y. Hu, R. Song, P. Rao, and Y. Wang, "Coarse-to-Fine PatchMatch for Dense Correspondence," IEEE Trans. Circuits Syst. Video Technol., vol. 28, no. 9, pp. 2233–2245, 2018, doi: 10.1109/TCSVT.2017.2720175.
  15. R. Song, Y. Yuan, Y. Li, and Y. Wang, "Extra Sign Bit Hiding Algorithm Based on Recovery of Transform Coefficients," Circuits Syst. Signal Process., vol. 37, no. 9, pp. 4128–4135, 2018, doi: 10.1007/s00034-017-0740-1.
  16. Y. Hu, Y. Li, and R. Song, "Robust Interpolation of Correspondences for Large Displacement Optical Flow," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 4791–4799, doi: 10.1109/CVPR.2017.509.
  17. Y. Hu, R. Song, and Y. Li, "Efficient Coarse-to-Fine Patch Match for Large Displacement Optical Flow," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 5704–5712, doi: 10.1109/CVPR.2016.615.
  18. Y. Hu, R. Song, Y. Li, P. Rao, and Y. Wang, "Highly Accurate Optical Flow Estimation on Superpixel Tree," Image Vis. Comput., vol. 52, pp. 167–177, Aug. 2016, doi: 10.1016/j.imavis.2016.06.004.
  19. Y. Tian, Y. Wang, R. Song, and H. Song, "Accurate Vehicle Detection and Counting Algorithm for Traffic Data Collection," in 2015 Int. Conf. Connected Vehicles Expo (ICCVE), 2016, pp. 285–290, doi: 10.1109/ICCVE.2015.60.
  20. Y. Jia, Y. Wang, R. Song, and J. Li, "Decoder Side Information Generation Techniques in Wyner-Ziv Video Coding: A Review," Multimed. Tools Appl., vol. 74, no. 6, pp. 1777–1803, 2015, doi: 10.1007/s11042-013-1718-z.
  21. J. Y. Lin, R. Song, C.-H. Wu, T. Liu, H. Wang, and C.-C. J. Kuo, "MCL-V: A Streaming Video Quality Assessment Database," J. Vis. Commun. Image Represent., vol. 30, pp. 1–9, 2015, doi: 10.1016/j.jvcir.2015.02.012.

遥感影像智能处理

  1. J. Li, H. Wu, R. Song, et al., "DF-PEM: Dual-Flow Prompt-Expert Mamba for Multimodal Remote Sensing Incremental Classification," IEEE Trans. Geosci. Remote Sens., early access, Jan. 2026, doi: 10.1109/TGRS.2026.3674175.
  2. J. Li, H. Wu, R. Song, H. Xu, Y. Li, and Q. Du, "Physics-Guided Time-Interactive-Frequency Network for Cross-Domain Few-Shot Hyperspectral Image Classification," IEEE Trans. Neural Netw. Learn. Syst., vol. 37, pp. 438–452, 2026, doi: 10.1109/TNNLS.2025.3608294.
  3. J. Li, S. Duan, H. Xu, R. Song, et al., "NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment," IEEE Trans. Geosci. Remote Sens., early access, 2025, doi: 10.1109/TGRS.2025.3634312.
  4. J. Li, Y. Ji, H. Xu, R. Song, et al., "UAT: Exploring Latent Uncertainty for Semi-Supervised Object Detection in Remote-Sensing Imagery," IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–12, 2025, Art no. 5633212, doi: 10.1109/TGRS.2025.3586701.
  5. L. Liu, R. Song, J. Li, W. Wang, and Q. Wen, "ASMF: A Self-Supervised Atmospheric Scatter Model-Based Fusion Network for Infrared Image Enhancement," IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–13, 2025, Art no. 5004613, doi: 10.1109/TGRS.2025.3581064.
  6. J. Li, Z. Zhang, R. Song, H. Xu, Y. Li, and Q. Du, "Contrastive MLP Network Based on Adjacent Coordinates for Cross-Domain Zero-Shot Hyperspectral Image Classification," IEEE Trans. Circuits Syst. Video Technol., vol. 35, pp. 8377–8390, 2025, doi: 10.1109/TCSVT.2025.3549365.
  7. J. Li, D. Zhu, R. Song, H. Xu, Y. Li, and Q. Du, "Multi-Feature Interaction and Degradation Estimation Transformer for Spectral Compressive Imaging," IEEE Trans. Circuits Syst. Video Technol., early access, 2025, doi: 10.1109/TCSVT.2025.3543569.
  8. Y. Leng, J. Li, R. Song, Y. Li, and Q. Du, "Uncertainty-Guided Discriminative Priors Mining for Flexible Unsupervised Spectral Reconstruction," IEEE Trans. Neural Netw. Learn. Syst., early access, 2025, doi: 10.1109/TNNLS.2025.3526159.
  9. J. Li, H. Li, H. Xu, R. Song, Y. Li, and Q. Du, "Background Suppression Network With Attention Collapse Inhibited Transformer for Optical Remote Sensing Object Detection," IEEE Trans. Geosci. Remote Sens., vol. 63, pp. 1–13, 2025, Art no. 5602413, doi: 10.1109/TGRS.2024.3520299.
  10. J. Li, S. Du, R. Song, Y. Li, and Q. Du, "Progressive Spatial Information-Guided Deep Aggregation Convolutional Network for Hyperspectral Spectral Super-Resolution," IEEE Trans. Neural Netw. Learn. Syst., vol. 36, no. 1, pp. 1677–1691, Jan. 2025, doi: 10.1109/TNNLS.2023.3325682.
  11. J. Li, Z. Zhang, Y. Liu, R. Song, Y. Li, and Q. Du, "SWFormer: Stochastic Windows Convolutional Transformer for Hybrid Modality Hyperspectral Classification," IEEE Trans. Image Process., vol. 33, pp. 5482–5495, 2024, doi: 10.1109/TIP.2024.3465038.
  12. J. Li, S. Duan, Y. Leng, R. Song, Y. Li, and Q. Du, "Residual Mask in Cascaded Convolutional Transformer for Spectral Reconstruction," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–15, 2024, Art no. 5523615, doi: 10.1109/TGRS.2024.3427633.
  13. J. Li, Z. Zhang, R. Song, Y. Li, and Q. Du, "SCFormer: Spectral Coordinate Transformer for Cross-Domain Few-Shot Hyperspectral Image Classification," IEEE Trans. Image Process., vol. 33, pp. 840–855, 2024, doi: 10.1109/TIP.2024.3351443.
  14. J. Li, P. Tian, R. Song, H. Xu, Y. Li, and Q. Du, "PCViT: A Pyramid Convolutional Vision Transformer Detector for Object Detection in Remote-Sensing Imagery," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–15, 2024, Art no. 5608115, doi: 10.1109/TGRS.2024.3360456.
  15. J. Li, Y. Liu, R. Song, W. Liu, Y. Li, and Q. Du, "HyperMLP: Superpixel Prior and Feature Aggregated Perceptron Networks for Hyperspectral and LiDAR Hybrid Classification," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–14, 2024, Art no. 5505614, doi: 10.1109/TGRS.2024.3355037.
  16. K. Cao, J. Li, R. Song, Z. Liu, and Y. Li, "Model-Driven Deep Pipeline With Uncertainty-Aware Bundle Adjustment for Satellite Photogrammetry," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–13, 2024, Art no. 5605313, doi: 10.1109/TGRS.2024.3352072.
  17. C. Wu, J. Li, R. Song, Y. Li, and Q. Du, "HPRN: Holistic Prior-Embedded Relation Network for Spectral Super-Resolution," IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 8, pp. 11409–11423, Aug. 2024, doi: 10.1109/TNNLS.2023.3260828.
  18. J. Li, Y. Leng, R. Song, W. Liu, Y. Li, and Q. Du, "MFormer: Taming Masked Transformer for Unsupervised Spectral Reconstruction," IEEE Trans. Geosci. Remote Sens., vol. 61, pp. 1–12, 2023, Art no. 5508412, doi: 10.1109/TGRS.2023.3264976.
  19. J. Li, Y. Diao, R. Song, B. Xi, Y. Li, and Q. Du, "Class-Specific Autoaugment Architecture Based on Schmidt Mathematical Theory for Imbalanced Hyperspectral Classification," IEEE Trans. Geosci. Remote Sens., vol. 61, pp. 1–15, 2023, Art no. 5525315, doi: 10.1109/TGRS.2023.3317885.
  20. S. Duan, J. Li, R. Song, Y. Li, and Q. Du, "Unmixing-Guided Convolutional Transformer for Spectral Reconstruction," Remote Sens., vol. 15, no. 10, p. 2619, 2023, doi: 10.3390/rs15102619.
  21. K. Cao, J. Li, R. Song, and Y. Li, "HE²LM-AD: Hierarchical and Efficient Attitude Determination Framework With Adaptive Error Compensation Module Based on ELM Network," ISPRS J. Photogramm. Remote Sens., vol. 195, pp. 418–431, Jan. 2023, doi: 10.1016/j.isprsjprs.2022.12.010.
  22. C. Wu, J. Li, R. Song, Y. Li, and Q. Du, "RepCPSI: Coordinate-Preserving Proximity Spectral Interaction Network With Reparameterization for Lightweight Spectral Super-Resolution," IEEE Trans. Geosci. Remote Sens., vol. 61, pp. 1–13, 2023, Art no. 5508313, doi: 10.1109/TGRS.2023.3264675.
  23. J. Li, Y. Liu, R. Song, Y. Li, K. Han, and Q. Du, "Sal²RN: A Spatial–Spectral Salient Reinforcement Network for Hyperspectral and LiDAR Data Fusion Classification," IEEE Trans. Geosci. Remote Sens., vol. 61, pp. 1–14, 2023, Art no. 5500114, doi: 10.1109/TGRS.2022.3231930.
  24. J. Li et al., "Deep Hybrid 2-D–3-D CNN Based on Dual Second-Order Attention With Camera Spectral Sensitivity Prior for Spectral Super-Resolution," IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 2, pp. 623–634, Feb. 2023, doi: 10.1109/TNNLS.2021.3098767.
  25. Z. Liu, J. Li, R. Song, C. Wu, W. Liu, Z. Li, and Y. Li, "Edge Guided Context Aggregation Network for Semantic Segmentation of Remote Sensing Imagery," Remote Sens., vol. 14, no. 6, p. 1353, Mar. 2022, doi: 10.3390/rs14061353.
  26. J. Li, S. Du, R. Song, C. Wu, Y. Li, and Q. Du, "HASIC-Net: Hybrid Attentional Convolutional Neural Network With Structure Information Consistency for Spectral Super-Resolution of RGB Images," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2022, Art no. 5522515, doi: 10.1109/TGRS.2022.3142258.
  27. J. Li, Y. Ma, R. Song, B. Xi, D. Hong, and Q. Du, "A Triplet Semisupervised Deep Network for Fusion Classification of Hyperspectral and LiDAR Data," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2022, Art no. 5540513, doi: 10.1109/TGRS.2022.3213513.
  28. J. Li, S. Zi, R. Song, Y. Li, Y. Hu, and Q. Du, "A Stepwise Domain Adaptive Segmentation Network With Covariate Shift Alleviation for Remote Sensing Imagery," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2022, Art no. 5618515, doi: 10.1109/TGRS.2022.3152587.
  29. J. Li et al., "Feature Guide Network With Context Aggregation Pyramid for Remote Sensing Image Segmentation," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, pp. 9900–9912, 2022, doi: 10.1109/JSTARS.2022.3221860.
  30. B. Xi, J. Li, Y. Li, R. Song, D. Hong, and J. Chanussot, "Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification," IEEE Trans. Image Process., vol. 31, pp. 5079–5092, 2022, doi: 10.1109/TIP.2022.3192712.
  31. Y. Li, Y. Zheng, J. Li, R. Song, and J. Chanussot, "Hyperspectral Pansharpening With Adaptive Feature Modulation-Based Detail Injection Network," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–17, 2022, Art no. 5538117, doi: 10.1109/TGRS.2022.3206880.
  32. J. Li, H. Zhang, R. Song, W. Xie, Y. Li, and Q. Du, "Structure-Guided Feature Transform Hybrid Residual Network for Remote Sensing Object Detection," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–13, 2022, Art no. 5610713, doi: 10.1109/TGRS.2021.3103964.
  33. B. Xi et al., "Multi-Direction Networks With Attentional Spectral Prior for Hyperspectral Image Classification," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2022, Art no. 5500915, doi: 10.1109/TGRS.2020.3047682.
  34. B. Xi, J. Li, Y. Li, R. Song, W. Sun, and Q. Du, "Multiscale Context-Aware Ensemble Deep KELM for Efficient Hyperspectral Image Classification," IEEE Trans. Geosci. Remote Sens., vol. 59, no. 6, pp. 5114–5130, Jun. 2021, doi: 10.1109/TGRS.2020.3022029.
  35. J. Li, C. Wu, R. Song, Y. Li, and W. Xie, "Residual Augmented Attentional U-Shaped Network for Spectral Reconstruction From RGB Images," Remote Sens., vol. 13, no. 1, p. 115, Dec. 2020, doi: 10.3390/rs13010115.
  36. J. Li, C. Wu, R. Song, Y. Li, and F. Liu, "Adaptive Weighted Attention Network With Camera Spectral Sensitivity Prior for Spectral Reconstruction From RGB Images," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), 2020, pp. 462–463.
  37. J. Li et al., "Hyperspectral Image Super-Resolution by Band Attention Through Adversarial Learning," IEEE Trans. Geosci. Remote Sens., vol. 58, no. 6, pp. 4304–4318, Jun. 2020, doi: 10.1109/TGRS.2019.2962713.
  38. B. Xi et al., "Deep Prototypical Networks With Hybrid Residual Attention for Hyperspectral Image Classification," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 13, pp. 3683–3700, 2020, doi: 10.1109/JSTARS.2020.3004973.
  39. J. Li, R. Cui, B. Li, R. Song, Y. Li, and Q. Du, "Hyperspectral Image Super-Resolution With 1D–2D Attentional Convolutional Neural Network," Remote Sens., vol. 11, no. 23, p. 2859, Dec. 2019, doi: 10.3390/rs11232859.
  40. J. Li, Y. Li, R. Song, S. Mei, and Q. Du, "Local Spectral Similarity Preserving Regularized Robust Sparse Hyperspectral Unmixing," IEEE Trans. Geosci. Remote Sens., vol. 57, no. 10, pp. 7756–7769, Oct. 2019, doi: 10.1109/TGRS.2019.2916296.

教学

Courses

《工程优化》

授课对象：大二第二学期课程性质：选修课学时数：32

教学目标：通过本课程的学习，使学生对高等数学、矩阵等知识在实际工程中的应用方法有总体认识，对于如何将工程中的问题转化为数学问题有清晰明确的思路，能够用最优化的方法得出工程问题的近似最优解。为机器学习、数据挖掘、深度学习等后续课程的学习打好基础。

课件资源：下载链接提取码：und5

《计算机通信网》

授课对象：大三第二学期课程性质：选修课学时数：80

教学目标：使学生掌握计算机通信网的基本概念和体系结构、网络协议机制及重要协议内容、网络通信问题的基本分析方法，以及网络通信技术的发展趋势和新进展，强调系统理解与工程应用能力培养。

课件资源：下载链接提取码：mb6l
Writing Resources

硕士论文 LaTeX 模板

CVIA 组建议硕士论文采用 LaTeX，以减少排版导致的时间浪费，并实现内容与版式分离。西安电子科技大学研究生院官网提供了硕士论文 LaTeX 模板，图像所往届研究生也修正了模板中的若干问题。

官方模板：研究生院官方模板链接
修正版模板：图像所修改 2021.01 版

本科毕设论文 LaTeX 模板

2020 届本科生崔元顺在 GitHub 上共享了本科毕设论文模板，建议参加本科毕设的学生基于该模板完成论文撰写。

模板链接：GitHub 仓库

招生

最新动态

news icon2026 年硕士新增一个学硕指标：欢迎感兴趣的学子邮件咨询，工作时间通常可较快回复，并可进一步安排腾讯会议面聊。

news icon2026 年博士仍有可用指标：欢迎对计算机视觉、图像分析、三维空间测量和 6D 位姿估计方向感兴趣的研究生联系。

实验室需要的

  • 通信、电子、计算机、测绘等相关专业背景。
  • 诚实可信、责任心强、脚踏实地、精益求精。
  • 具有较强的主动思维能力。
  • 具备良好的数学基础、逻辑思维能力和英语读写能力。

实验室能提供的

  • 入学培训：研究课题介绍、科研基础技能训练、文献阅读方法、科研方法与论文撰写训练。
  • 科研环境：提供科研所需的基础设备与资料支持。
  • 学术指导：每周至少一次组会，并结合兴趣与任务安排一对一指导。
  • 培养方式：团队在研究生培养过程中不区分学术型与专业型硕士，更关注个人兴趣、能力和专长，支持算法研究与工程系统研究两条路径。

报考联系与材料

  • 在报考前请将学校教务处认可的四年成绩单发送至邮箱，并标记最感兴趣的三门课程。
  • 附上个人简历，尽量详细展示竞赛、实践和项目经历。
  • 附上英语成绩，如 CET-6、TOEFL、GRE 或雅思。
  • 请特别补充数学课程和编程能力相关信息，如高等数学、线性代数，以及 C/C++、Verilog、Python 等课程成绩。
  • 发送邮件时建议要求回执，并在一周内确认收到收条。

团队培养与去向

  • 博士研究生毕业主要去向：高校任职、研究所、科技企业；当前在读博士 2 人，已毕业博士 5 人。
  • 硕士研究生毕业主要去向包括 Intel、华为、中兴、荣耀、海思、字节跳动、百度，以及中电集团、航天科技集团、中航工业集团和中国科学院下属研究所等；当前在读硕士 23 人，已毕业硕士 103 人。
  • 如需推荐信，请确保教师已对你有足够了解。