下划线：课题组学生，星号*：通讯作者

技术报告

[4] M. Li, L. Zhang, M. Yang, et al., "Scene Scale Prediction Network for Generalizable Monocular Depth Estimation," 2025.

[2] B. Chen, M. Yang, et al., "Joint Absolute-Relative Relation Network for Generalizable Depth Completion," 2025.

[1] X. Zhou, M. Yang, et al., "End-to-End 3D Object Detection with Depth Sructure and Location Contraints," 2023. 

期刊论文（部分）

[29] 郑南宁，杨勐，姜维周，孙宏滨，丁宁，具身智能发展趋势与展望，中国工程科学，2026年1月。

[28] 郑南宁，杨勐，汪建基，蒋才桂，辛景民，人工智能本科专业大学物理课程改革与实践，计算机教育，2025年12月。

[27] D. Suzhang, L. Zhang, M. Yang*, et al., "Relative RGB-Depth Structure Network for Generalizable Depth Map Recovery," 2026. [link]

[26] Z. Kuang, R. Ding, M. Yang*, et al., "Object-Scene-Camera Decomposition and Recomposition for Data Efficient Monocular 3D Object Detection", International Journal of Computer Vision (IJCV), Jan. 2026.

[25] R. Ding, Z. Kuang, M. Yang*, et al., "Multi-modal Decouple-Recouple Network for Robust 3D Object Detection," IEEE Trans. Circuits Syst. Video Technol. (T-CSVT), Jan. 2026.

[24] L. Zhang, M. Li, M. Yang*, et al., "Relative Depth Knowledge Distillation for Generalizable Monocular Depth Estimation," Neurocomput., Jan. 2026.

[23] S. Liu, D. Suzhang, M. Yang*, et al., "Depth Map Super-Resolution via Cross-modality and Cross-scale Guidance," IEEE Trans. Multimedia (T-MM), Mar. 2025.

[22] H. Wang, M. Yang*, et al., "Scale Propagation Network for Generalizable Depth Completion," IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), 2025.

[21] H. Cao, X. Zhao, A. Li, and M. Yang*, "Depth Image Rectification Based on an Effective RGB–Depth Boundary Inconsistency Model," Electronics, Aug. 2024.

[20] C. Wei, M. Yang*, et al., "FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene," IEEE Trans. Circuits Syst. Video Technol. (T-CSVT), Nov. 2024.

[19] R. Ding, M. Yang*, et al., "Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection," IEEE Trans. Circuits Syst. Video Technol. (T-CSVT), Oct. 2024.

[18] H. Wang, M. Yang*, et al., "G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB-X Data," IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI), May 2024.

[17] M. Yang*, L. Zhang, D. Suzhang, C. Zhu, and N. Zheng, "Misaligned RGB-Depth Boundary Identification and Correction for Depth Image Recovery," IEEE Trans. Broadcast. (T-BC), Mar. 2024.

[16] H. Wang, M. Yang*, C. Zhu, and N. Zheng, "RGB-Guided Depth Map Recovery by Two-Stage Coarse-to-Fine Dense CRF Models,"  IEEE Trans. Image Process. (T-IP), Jan. 2023.

[15] D. Ren, M. Yang*, J. Wu, et al., "Surface Normal and Gaussian Weight Constraints for Indoor Depth Structure Completion," Pattern Recognition (PR), Jan. 2023.

[14] H. Wang, M. Yang*, X. Lan, C. Zhu, and N. Zheng, "Depth Map Recovery based on a Unified Depth Boundary Distortion Model," IEEE Trans. Image Process. (T-IP), 2022.

[13] P. Hao, M. Yang*, et al., "Subjective Low-Light Image Enhancement based on a Foreground Saliency Map Model," Multimedia Tools and Applications (MTA), 2021.

[12] M. Yang, C. Zhu, X. Lan, and N. Zheng, "Efficient Estimation of View Synthesis Distortion for Depth Coding Optimization," IEEE Trans. Multimedia (T-MM), Apr. 2019.

[11] M. Yang and N. Zheng. "SynBF: A New Bilateral Filter for Post-removal of Noise from Synthesis Views in 3D Video," IEEE Trans. Multimedia (T-MM), Jan. 2019.

[10] M. Yang, F. Wang, Y. Wang, and N. Zheng, "A Denoising Method for Randomly Clustered Noise in ICCD Images Based on Hypergraph Cut and Down Sampling," Sensors, Dec. 2017.

[9] M. Yang, N. Zheng, C. Zhu, and F. Wang, "A Novel Method of Minimizing View Synthesis Distortion Based on Its Non-monotonicity in 3D Video," IEEE Trans. Image Process. (T-IP), Nov. 2017.

[8] X. Li, X. Lan, M. Yang, J. Xue, and N. Zheng, "A New Compressive Sensing Video Coding Framework Based on Gaussian Mixture Model," Signal Process.-Image Comm., Jul. 2017.

[7] F. Wang, Y. Wang, M. Yang*, et al., "A Denoising Scheme for Randomly Clustered Noise Removal in ICCD Sensing Images," Sensors, Jan. 2017.

[6] J. Li, X. Lan, J. Wang, M. Yang, et al., “Fast additive Quantization for Vector Compression in Nearest Neighbor Search,” Multimedia tools and Applications (MTA), Nov. 2016. 

[5] X. Li, X. Lan, M. Yang, J. Xue, and N. Zheng, "Efficient Lossy Compression for Compressive Sensing Acquisition of Images  in Compressive Sensing Imaging Systems," Sensors, Dec. 2014.

[4] M. Yang, T. Groves, N. Zheng, and P. Cosman, “Iterative Pricing-Based Rate Allocation for Video Streams with Fluctuating Bandwidth Availability,” IEEE Trans. Multimedia (T-MM), Nov. 2014.

[3] M. Yang, X. Lan, N. Zheng, and P. Cosman, “Depth-Assisted Temporal Error Concealment for Intra Frame Slices in 3D Video,” IEEE Trans. Broadcast. (T-BC), June 2014.

[2] M. Yang, X. Lan, and N. Zheng, “Adaptive Multiple Description Coding for Hybrid Networks with Dynamic PLR and BER,” Signal Process.- Image Comm., Oct. 2013.

[1] X. Lan, M. Yang, Y. Yuan, S. Zhao, and N. Zheng, “Adaptively Post-Encoding Multiple Description Video Coding,” Neurocomput., Feb. 2013.

会议论文（部分）

[24] Z. Kuang, R. Ding, H. Wang, M. Yang*, et al., "CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection," IEEE/CVF CVPR, June 2026.

[23] R. Ding, Z. Kuang, M. Yang*, et al., "RayD3D: Distilling Depth Knowledge along the Ray for Robust Multi-view 3D Object Detection," AAAI, Jan. 2026.

[22] H. Wang, A. Xiao, X. Zhang, M. Yang*, et al., "PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency," IEEE ICCV, Oct. 2025.

[21] F. Li, R. Ding, M. Yang*, et al., "Consistent Feature Alignment for Cross-Modal Knowledge Distillation in Monocular 3D Object Detection," IEEE/RJS IROS, Hangzhou, Oct. 2025.

[20] X. Luo, L. Dang, M. Yang, et al., "LSTM with AhI-model based Kalman Filter for Lithium-ion Battery State of Charge Estimation," CAC, Qingdao, Nov. 2024.

[19] Y. Ji, Y. Chen, L. Yang, R. Ding, M. Yang, et al., "VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception," NeurIPS, Vancouver, Canada, Dec. 2024.

[18] R. Wang, R. Chen, M. Yang*, et al., "Multi-modal Camera and One-beam LiDAR Fusion Network for Low-cost 3D Object Detection," IEEE ROBIO, Bangkok, Thailand, Dec. 2024.

[17] L. Zhang, and M. Yang*, "RGB-Depth Structure Similarity for Self-supervised Monocular Depth Estimation," IEEE RCAR, Taiyuan, July 2023.

[16] Z. Zhao, and M. Yang*, "RGB-based No-Reference Depth Map Quality Assessment Method," IEEE BMSB, Chengdu, Aug. 2021.

[15] R. Huang, K. Zhu, S. Chen, T. Xiao, M. Yang, and N. Zheng, "A High-Precision and Robust Odometry based on Sparse MMW Radar Data and A Large-Range and Long-Distance Radar Positions Data Set," IEEE ITSC, Indianapolis, IN, USA, 2021.

[14] M. Yang, Y. Cheng, Y. Guang, J. Wang, and  N. Zheng, "Boundary Recovery of Depth Map for Synthesis View Optimization in 3D Video," IEEE ICCE, Las Vegas, Jan. 2019.

[13] Y. Cheng, M. Yang, and S. Li, "Boundary Artifacts Removal of Synthesis View by Pre-filtering the Texture Image in 3D Video, " CAC, Xi'an, Nov. 2018. 

[12] Tiannan Dong, Jianji Wang, Meng Yang, Kai Yi, and Nanning Zheng, "Affine LBG Codebook Training of Univariate Linear Representation," IEEE GlobalSIP, Anaheim, CA, Nov. 2018.

[11] M. Yang, N. Zheng, F. Wang, and C. Zhu, "A New Bilateral Filter for Post-removing the Noise of Synthesis View in 3D Video," APSIPA ASC, Kuala Lumpur, Dec. 2017.

[10] Y. Wang, M. Yang*, et al., "A Hypergraph-cut Based Denoising Algorithm for Randomly Clustered Noise Removal in ICCD Images," CAC, Jinan, Oct. 2017.

[9] K. Wang, X. Lan, X. Li, M. Yang, and N. Zheng, "Compressive Sensing Depth Video Coding via Gaussian Mixture Models and Object Edges," PCM, Harbin, Sep. 2017.

[8] X. Li, X. Lan, M. Yang, J. Xue, and N. Zheng, "Efficient Compressive Sensing Video Compression Method Based on Gaussian Mixture Models," IEEE VCIP, Chengdu, Nov. 2016.

[7] J. Chen, X. Lan, and M. Yang, "Efficient Detail-enhanced Exposure Correction Based on Auto-fusion for LDR Image," IEEE MMSP, Montreal, Sep. 2016.

[6] Q. Xue, X. Lan, and M. Yang, "Depth Map Coding by Modeling the Locality and Local Correlation of View Synthesis Distortion in 3D Video," IEEE MMM, Miami, Jan. 2016.

[5] X. Li, X. Lan, M. Yang, J. Xue, and N. Zheng, "Optimized Truncation Model for Adaptive Compressive Sensing Acquision of Images," IEEE VCIP, Singapore, Dec. 2015.

[4] M. Yang, C. Zhu, X. Lan, and N. Zheng, "Parameter-free View Synthesis Distortion Model with Application to Depth Video Coding," IEEE ISCAS, Lisbon, May 2015.

[3] X. Li, X. Lan, M. Yang, J. Xue, and N. Zheng, "Universal and Low-complexity Quantizer Design for Compressive Sensing Image Coding," IEEE VCIP, Kuching, May 2013.

[2] M. Yang, Y. Yang, P. Cosman "Depth-Assisted Error Concealment for Intra Frame Slices in 3D Video," IEEE ICIP, Orland, May 2012.

[1] M. Yang, X. Lan, and N. Zheng, "Explicit Network-adaptive Robust Multiple Description Coding," IEEE DCC, Snowbird, Mar. 2011.

发明专利

[26] 杨勐，张睿哲，王昊天，"基于合成大量伪几何结构的可泛化深度补全方法及系统"，申请号：2025114143032，2025年9月29日。

[25] 杨勐，张禹，丁瑞，郑南宁，"一种基于选择性知识蒸馏的单目三维目标感知方法及系统"，申请号：2025106427761，2025年5月19日。

[24] 杨勐，邝兆年，丁瑞，郑南宁，“一种用于单目3D目标检测的数据增强方法及系统”，申请号：2024119412721，2024年12月26日。（已授权）

[23] 杨勐，吴江凡，丁焱，张禹，任鹏举，郑南宁，"一种轻量化的多AMR协同感知方法及系统"，申请号：2024107389391，2024年6月7日。

[22] 杨勐，陈荣海，王荣鑫，郑南宁，"一种面向开放场景的弱监督3D目标检测方法及系统"，申请号：2024106182990，2024年5月17日。

[21] 杨勐，刘书哲，郑南宁，"基于跨模态多尺度特征引导的深度图超分辨率方法及系统"，申请号：2024106182971，2024年5月17日。

[20] 杨勐，魏成睿，郑南宁，"可泛化通用单目绝对深度图估计方法、系统、芯片及设备"，申请号：2024102156874，2024年2月27日。

[19] 杨勐，王荣鑫，郑南宁，"基于单线激光雷达和单目相机的三维目标检测方法及系统",申请号：2024102230497，2024年2月28日。

[18] 杨勐，罗祥咏，张向波，党路娟，陈霸东，“一种基于LSTM-EA框架的电池SOC预测方法及系统”，申请号：2024102156802，2024年2月27日。

[17] 杨勐，王昊天，郑南宁，“一种基于尺度传播归一化层的零样本深度补全方法及系统”，申请号：2024102156836，2024年2月27日。

[16] 杨勐，丁瑞，郑南宁，“一种基于单目相机的跨模态蒸馏3D目标检测方法及系统”，申请号：202311786873.5，2023年12月23日。

[15] 杨勐，王昊天，郑南宁，“可泛化的通用单目深度图推理方法、系统、介质及设备”，申请号：202310180743.0，2023年2月28日。

[14] 杨勐，温源，丁焱，陈荣海，王荣鑫，吴江凡，任鹏举，郑南宁，“一种基于环境感知的3D目标检测方法及系统”，申请号：2023102146632，2023年3月7日。

[13] 杨勐，赵大龙，丁焱，陈荣海，王荣鑫，任鹏举，郑南宁，“一种兼容局部避障功能的多AGV导航方案”，申请号：202310215192.7，2023年3月7日。

[12] 任鹏举，焦崇珊，丁焱，毛艺钧，杨勐，郑南宁，“一种多AGV协同感知方法”，申请号：2022113219558，2022年11月1日。

[11] 任鹏举，毛艺钧，丁焱，焦崇珊，杨勐，郑南宁，“基于优先级的集中式多AGV多径通道变道决策规划方法”，申请号：2022113219543，2022年11月1日。

[10] 任鹏举，毛艺钧，丁焱，焦崇珊，杨勐，郑南宁，“基于流量的多AGV全局调度方法”，申请号：2022113231776，申请号：2022年11月1日。

[9] 杨勐，周祥，丁瑞，郑南宁，“一种基于平面约束与位置约束的3D目标检测方法及系统”，申请号：202310028861.X，2022。（已授权）

[8] 杨勐，任东冉，郑南宁，“一种弱对齐RGB-D图像引导的深度图补全方法及系统”，申请号：202211064275.2，2022年8月31日。（已授权）

[7] 杨勐，任东冉，郑南宁，“一种基于法向量和高斯权重约束的深度图像补全方法及系统”，申请号：ZL202110574430.4，2021年5月。（已授权）

[6] 杨勐，王昊天，郑南宁，”基于两层全连接条件随机场模型的深度图结构修复方法“，申请号：ZL202111057715.2，2021年11月。（已授权）

[5] 杨勐，王昊天，郑南宁，“一种基于RGB-D的SSIM结构相似度的迭代深度图结构修复方法”，申请号：ZL200010007508.X，2020年1月。(已授权)

[4] 杨勐，陈翔，光宇杰，郑南宁，“一种基于引导滤波器的鲁棒深度图结构重建和去噪方法”，申请号：ZL202010007506.0，2020年1月。(已授权)

[3] 杨勐，郝鹏程，王爽，郑南宁，“一种基于显著性前景内容的低光照图像增强方法”，申请号：ZL202010056934.2，2020年1月16日。(已授权)

[2] 杨勐，马勇，郑南宁，“一种基于单视点RGB-D图像的大尺度全景视点合成方法”，申请号：ZL202010113813.7，2020年2月24日。(已授权)

[1] 杨勐，光宇杰，成钰，郑南宁，“一种基于彩色图引导的深度图恢复及视点合成优化方法”，申请号：ZL201810600927.7，2018年6月。（已授权）