李杨，南京大学电子科学与工程学院，博士，副教授，硕士生导师，2000年和2003年与东南大学分别获工学学士和工学硕士学位，2006年毕业于南京大学电子科学与工程系，获工学博士学位，2012-2014年美国西北大学博士后。长期从事视觉环境感知、深度估计与重建等计算机视觉理论与应用课题研究，学科骨干教师，发表国际学术论文50余篇，获得发明专利授权10余项。获得2005年度华英文教基金青年教师奖； 2009江苏省年度优秀科技创新团队成员， 2012年度中国计算机行业发展成就优秀方案与案例。2017年度南京市高层次创新创业人才。

      研究主页： https://nju-ee.github.io/

主要研究方向

1. 视觉深度感知与三维重建.
2. 生物图像信息学.

研究方向简介

       在计算机视觉领域。我们的研究兴趣集中利用计算机视觉技术对环境进行三维感知和对环境图像进行语义理解。我们围绕着机器人导航、自动驾驶等应用场景下的多种三维感知技术进行研究。在双目及多目立体视觉被动感知技术方面，我们首次提出了利用帧间相关性加速视频序列中的立体匹配问题，该方法在不降低视差计算精度的前提可以显著提升基于深度学习和非深度学习方法的立体匹配速度，我们在嵌入式系统中实现的双目立体视觉系统达到了国际先进水平。我们同时在激光雷达点云的语义分割、配准上也取得众多成果，利用算法优化和GPU加速我们实现在低功耗嵌入式平台上的实时三维重建。针对机器人导航、自动驾驶等应用场景，我们进一步发展和完善了双目视觉的同步定位与地图构建问题，提出并实现了利用深度图像加速地图构建。此外，我们在目标识别、图像语义分析等领域也取得若干成果，例如我们针对多模态图像中的目标识别问题提出了全新的深度网络架构和数据增强及训练方法，显著提升了算法的性能。

       在生物图像信息学领域。我们关注机器学习、计算机视觉理论在生物医学工程、生命科学等交叉学科领域的应用研究。我们发展了一系列采用计算机视觉技术对荧光显微图像中的细胞进行高通量量化分析的工具：AxonQuant，MitoQuant等，用以帮助生命科学家在微观层面对细胞的形态、动力学特征进行分析，我们首次提出了线粒体的速度空间分布动力学模型，这些方法和工具或得了领域内科学家的广泛认同和关注。我们同时开展了荧光显微图像增强及超分辨率显微成像中的单分子定位问题的研究，我们提出的移变点扩散函数模型极大的提升了真实荧光显微图像的反卷积重建结果，这个模型在单分子亚像素定位、光片显微图像增强等领域都加大的应用潜力。

      上述研究成果得以在ECCV、Optcal Express等领域内有影响力的国际期刊及会议发表，同时我们也取得了若干中国发明专利授权。

面向本科生开设《数字图像处理》课程；
面向本科生及研究生开设《计算机视觉》课程。

2026年

· M. Li, X. Hu, Z. Gao, S. Du, and Y. Li, “Enhancing multi-view omnidirectional depth estimation with semantic-aware cost aggregation and spatial propagation,” IEEE Trans. Circuits Syst. Video Technol., 2026, Early Access. 

· JCR分区Q1，中科院 1区

2025年

· C. Wu, J. Li, J. Cao, M. Li, S. Du, and Y. Li, “OmniOcc: Cylindrical voxel-based semantic occupancy prediction for omnidirectional vision systems,” IEEE Access, vol. 13, pp. 139944–139952, 2025.  JCR分区Q2

· J. Wu, J. Li, J. Wang, X. Xu, S. Du, and Y. Li, “Joint modeling of pixel-wise visibility and fog structure for real-world scene understanding,” Atmosphere, vol. 16, no. 10, p. 1161, 2025. JCR分区Q2

· Y. Xu, B. Zhai, Y. Sun, M. Li, Y. Li, and S. Du, “HiFi-Portrait: Zero-shot identity-preserved portrait generation with high-fidelity multi-face fusion,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2025. CCF A会议

· J. Li, C. S. Low, J. Cao, S. Du, and Y. Li, “Authentic 3D structure preserved surround view system for automobile driving assistance,” in Proc. IEEE Int. Conf. Syst., Man, Cybern. (SMC), Vienna, Austria, 2025, pp. 7121–7130. CCF C会议

2024年

· T. Tang, J. Cao, X. Yang, S. Liu, D. Zhu, S. Du, and Y. Li, “A real-time method for railway track detection and 3D fitting based on camera and LiDAR fusion sensing,” Remote Sens., vol. 16, no. 8, p. 1441, 2024. JCR分区Q1，中科院2区

· P. Wang, M. Li, J. Cao, S. Du, and Y. Li, “CasOmniMVS: Cascade omnidirectional depth estimation with dynamic spherical sweeping,” Appl. Sci., vol. 14, no. 2, p. 517, 2024. JCR分区Q2，中科院4区

· Feng, Y., Shuai, J., Wang, P., Li, Y., & Du, S. (2025). A Stereo Matching Method for Specular Objects via Cascaded Network and Joint Supervision. In: Z. Lin, MM. Cheng, R. He, K. Ubul, W. Silamu, H. Zha, J. Zhou, & CL. Liu (Eds.), Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol. 15033, pp. 118–129. Springer, Singapore. CCF C会议

2023年

· Z. Zhu, S. Liu, J. Shuai, S. Du, and Y. Li, “3D associative embedding: Multi-view 3D human pose estimation in crowded scenes,” in Proc. ACM Conf. Netw. Internet Things (CNIOT), 2023, pp. 131–139. EI会议

· S. Liu, J. Shuai, Y. Li, and S. Du, “MMDA: Multi-person marginal distribution awareness for monocular 3D pose estimation,” IET Image Process., vol. 17, pp. 2182–2191, 2023. JCR分区Q3，中科院4区

2022年

· J. Wang, C. Peng, M. Li, Y. Li, and S. Du, “The study of stereo matching optimization based on multi-baseline trinocular model,” Multimedia Tools Appl., vol. 81, pp. 12961–12972, 2022. JCR分区Q2，中科院分4区

· M. Li, X. Jin, X. Hu, J. Dai, S. Du, and Y. Li, “MODE: Multi-view omnidirectional depth estimation with 360° cameras,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2022, pp. 197–213. CCF B类会议

· X. Hu, J. Dai, M. Li, C. Peng, Y. Li, and S. Du, “Online human action detection and anticipation in videos: A survey,” Neurocomputing, vol. 491, pp. 395–413, 2022. JCR分区Q2中科院 2区

· Z. Li, S. Liu, J. Bai, C. Peng, Y. Li, and S. Du, “A novel skeleton-based model with spine for 3D human pose estimation,” in Proc. IEEE Int. Conf. Consum. Commun. Netw. Conf. (CCNC), 2022, pp. 0501–0506.

2021年

· T. Chen, C. Peng, M. Li, X. Chen, S. Du, and Y. Li, “A review on quantitative analyzing axonal transport of mitochondria,” in Proc. IEEE Int. Conf. e-Health Bioeng. (LifeTech), 2021, pp. 441–443.

· Q. Li, C. Peng, Y. Ma, S. Du, B. Guo, and Y. Li, “Pixel-level diabetic retinopathy lesion detection using multi-scale convolutional neural network,” in Proc. IEEE Int. Conf. e-Health Bioeng. (LifeTech), 2021, pp. 438–440.

· M. Li, X. Hu, J. Dai, Y. Li, and S. Du, “Omnidirectional stereo depth estimation based on spherical deep network,” Image Vis. Comput., vol. 114, p. 104264, 2021. JCR分区Q2，中科院分区 3区

· X. Jin, M. Li, C. Peng, S. Du, and Y. Li, “Depth-based removal of thermal reflection with the light-field theory,” J. Opt. Soc. Am. A, vol. 38, pp. 1594–1602, 2021. JCR分区Q3，中科院分区 4区

· J. Cao, C. Peng, Y. Li, and S. Du, “A shadow detection method for retaining key objects in complex scenes,” in Proc. Int. Conf. Knowl. Sci. Eng. Manag. (KST), 2021, pp. 90–95.

· J. Bai, C. Peng, Z. Li, S. Du, and Y. Li, “A study of general data improvement for large-angle head pose estimation,” in Proc. Int. Conf. Comput. Anal. Images Patterns (CAIP), 2021, pp. 199–209.

· H. Wang, M. Li, J. Wang, Y. Li, and S. Du, “A discussion of optimization about stereo image depth estimation based on multi-baseline trinocular camera model,” in Proc. Int. Conf. Comput. Sci. Comput. Intell. (CSCI), 2021, pp. 1716–1720.

2020年以前（部分）

· J. Wang, C. Peng, M. Li, X. Chen, S. Du, and Y. Li, “Stereo Matching Optimization with Multi-baseline Trinocular Camera Model,” in Proc. IEEE Can. Conf. Elect. Comput. Eng. (CCECE), 2020, pp. 1–4. JCR分区 Q4 ，CCF-C会议

· X. Chen, M. Li, T. Chen, S. Du, and Y. Li, “Estimating the Binding and Unbinding Rate of Motor Protein from Mitochondrial Motion,” in Proc. IEEE Global Conf. Life Sci. Technol. (LifeTech), 2020, pp. 1–2.

· M. Li, L. Shi, X. Chen, S. Du, and Y. Li, “Using Temporal Correlation to Optimize Stereo Matching in Video Sequences,” IEICE Trans. Inf. Syst., vol. E102-D, no. 6, pp. 1234–1245, 2019. JCR分区:Q4 ，中科院4区

· S. Lu, T. Chen, F. Yang, C. Peng, S. Du, and Y. Li, “Minimal Path based Particle Tracking in Low SNR Fluorescence Microscopy Images,” in Proc. Int. Conf. Biomed. Image Process. (ICBIP), 2019, pp. 1–5.

· M. Li, X. Chen, C. Peng, S. Du, and Y. Li, “Modeling the occlusion problem in thermal imaging to allow seeing through mist and foliage,” J. Opt. Soc. Am. A, vol. 36, no. 2, pp. A67–A75, 2019. JCR分区 Q3，中科院3区

· F. Yang, S. Lu, S. Du, Y. Li, “A Novel Training Method for Faster R-CNN based Object Detection in Multi-modal Images,” in Imaging and Applied Optics, OSA, 2018.

· Y. Chen, M. Chen, L. Zhu, S. Du, and Y. Li, “Measure and model a 3-D space-variant PSF for fluorescence microscopy image deblurring,” Opt. Express, vol. 26, no. 11, pp. 14375–14391, 2018. JCR分区：Q1，中科院分区: 1区

· M. Chen, Y. Li, M. Yang, X. Chen, Y. Chen, F. Yang, S. Lu, S. Yao, T. Zhou, and J. Liu, “A new method for quantifying mitochondrial axonal transport,” Protein Cell, vol. 7, no. 11, pp. 804–819, 2016. JCR分区: Q1 ，中科院分区: 1区 

· Y. Li, M. Yang, Z. Huang, X. Chen, M. T. Maloney, L. Zhu, J. Liu, Y. Yang, S. Du, X. Jiang, and J. Y. Wu, “AxonQuant: A Microfluidic Chamber Culture-Coupled Algorithm That Allows High-Throughput Quantification of Axonal Damage,” Neurosignals, vol. 22, no. 3-4, pp. 1–16, 2014. JCR分区:Q4 ，中科院4区