三维重建，深度估计，多模态大模型，具身智能

Google Scholar  

2022- 现在        上海交通大学    长聘教轨副教授/博导 

2021-2022        香港大学（The University of Hong Kong）    博士后研究员 

2018-2021        阿德莱德大学（The University of Adelaide）    博士后研究员

2012-2019    上海交通大学    工学博士 

2008-2012    西安交通大学    工学学士

《计算机模式识别》   研究生课程       秋季学期

《模式识别导论》        本科生课程       秋季学期

1. 疾病诊断智能体可信推理与决策规划，新一代人工智能国家科技重大专项课题，407.74万，2026-2028，课题负责人

2. 面向航空器设计的跨模态智能数据库构建与生成式方法研究，校内AI for Science行业应用重点项目，100万，2025-2026，联合主持

3. 模型和数据驱动的快速图像滤波关键技术研究，国家基金委青年基金项目，30万，2025-2027，主持
   

4. 模型驱动图像滤波方法及其应用， 国家基金委优秀青年项目（海外），100万，2024-2026，主持

5. 模型数据驱动的图像和视频滤波增强方法及其应用，上海市科技委浦江人才项目，30万，2022-2024，主持

6. 华为ExploreX人才基金项目，华为企业人才基金，45万，2024-2026，主持

7. 统一图像和空间的视觉语言预训练大模型研究，华为企业横向，101.97万，主持

8. 校级科研启动经费，上海交大，80万，主持

9. 人才计划配套经费，上海交大，59万，主持
   

2026

1. Gao, X., Wu, X., Ning, Z., Yang, R., Zheng, Z.*, Yang, J.*, Liu, W.* (2026) AdaDepth: Exploiting Inherent Scene Information for Self-Supervised Depth Estimation in Dynamic Scenes, AAAI Conference on Artificial Intelligence (AAAI).

2. Ying, G., Zhang, D., Yang, C., Liu, W., Jeon, S. W., Wang, H., Huang, C., Zheng, Z. (2026, March). Exploiting All Mamba Fusion for Efficient RGB-D Tracking. AAAI Conference on Artificial Intelligence (AAAI).

3. Ning, Z., Gao, X., Cao, J., Yang, R., Xu, H., Zhu, X., Yang, J.*, Liu, W.* (2026) Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection, International Conference on Learning Representations (ICLR).

4. Liu, X., Shi, X., Pan, Y., Gu, S., Liu, W., Ren, C. (2026) D2S-RSG-SSD: Dual Double-Sampling with Random Sub-Samples Generation for Self-Supervised Real Image Denoising. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

5. Gao, X., Ning, Z., Zhang, G., Cao, J., Yang, R., Zheng, Z., Yang, J., Xiao, R., Liu, W.*  (2026) RoSAMDepth: Robust Self-supervised Depth Estimation Leveraging Segment Anything Model. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

6. Nian, B., Tang, F., Ning, Z., Jiang, D., Li, Y., Yang, J., Xiao, R., Zhou, S.K., Liu, W.* (2026) ProSM: Progressive Soft Masking for Fine-Grained Remote Image Segmentation. Findings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Findings).

7. Zhou, C., Wu, T., Liu, W., Wu, X., Fu, Y. (2026) MVSSM: Motion-aware Visual State Space Model for Efficient Video Deblurring. Findings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Findings).

8. Fu, Y., Zhou, C., Cheng, W., Wu, T., Li, Q., Wu, X.*, Liu, W.* (2026) EDVD: Cross-modal Spatio-Temporal Fusion with Event and Diffusion for Video Deblurring. IEEE Transactions on Image Processing (TIP).

9. Ning, Z., Gao, X., Cao, J., Zhang, G., Ma, S., Tong, W., Deng, H., Yang, J., Liu, W.* (2026) V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning. International Conference on Machine Learning (ICML).

10. Yang, Z.,  Zhu, Y., Chen, X.,  Liu, W., Xu, H. (2026) Physics-Based Dynamic Filtering with Diffusion Priors for Image Deblurring. ACM Multimedia (MM). 

11. Chen, X., Li, X., Sun, W., Zhang, W., Tian, C., Liu, W.* (2026), Asymmetric Invertible Disentanglement for Image Deraining. IEEE Transactions on Image Processing (TIP).

    
    

2025

1. Asada, M., Azeemb, W., Alic, A., Fang Y., Yang J.*, Zuo Y. and Liu W.* (2025) Inter-Modality Feature Representation Learning-based Fusion Network for 3D Industrial Defect Detection. Neural Networks (NN).

2. Nian, B., Tang, F., Ding, J., Yang, J., Zheng, Z., Zhou, S. K.*, & Liu, W.* (2025). SRS: Siamese Reconstruction-Segmentation Network based on Dynamic-Parameter Convolution. IEEE Transactions on Image Processing (TIP).

3. Ning, Z., Liu, Z., Gao, X., Zuo, Y.*, Yang, J.*, Fang, Y. & Liu, W.* (2025) CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Prediction. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

4. Tang, F., Nian, B., Ding, J., Ma, W., Quan, Q., Dong, C., Yang, J., Liu, W.*, Zhou, S. K.* (2025). Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation. In Proceedings of the 33st ACM International Conference on Multimedia (ACM MM).

5. Wang, B., Ning, Z., Ding, J.,Gao, X., Li, Y., Jiang, D., Yang, J.*, Liu, W.* (2025). Fix-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text. International Conference on Computer Vision (ICCV).

6. Asad, M., Azeem, W., Jiang, H., Mustafa, H. T., Yang, J.*, & Liu, W.* (2025). 2M3DF: Advancing 3D industrial defect detection with multi perspective multimodal fusion network. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

7. Chen, L., Liu, W.*, Wang, H., Jeon, S. W., Jiang, Y., & Zheng, Z.*(2025). Consistency-guided adaptive alternating training for semi-supervised salient object detection. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

8. Liu, S., Ding, J., Yang, J.*, & Liu, W.* (2025, April). Mixed Gaussian Splatting for High-Quality Rendering and Reconstruction. In Proceedings of 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.

9. Tang, F., Nian, B., Li, Y., Jiang, Z., Yang, J., Liu, W.*, & Zhou, S. K.* (2025). MambaMIM: Pre-training Mamba with state space token interpolation and its application to medical image segmentation. Medical Image Analysis (MIA), 103606.

10. Asad, M., Azeem, W., Malik, A. A., Jiang, H., Ali, A., Yang, J.*, & Liu, W.* (2025). 3D-MMFN: Multi-level multimodal fusion network for 3D industrial image anomaly detection. Advanced Engineering Informatics, 65, 103284.

11. Gao, X., Wang, B., Ning, Z., Yang, J.*, & Liu, W.* (2025). STDepth: Leveraging semantic-textural information in transformers for self-supervised monocular depth estimation. Computer Vision and Image Understanding (CVIU), 104422.

12. Chen, Y., Huang, X., Zhang, Q., Li, W., Zhu, M., Yan, Q., ... Liu W.*, & Hu, J.* (2025, April). Gim: A million-scale benchmark for generative image manipulation detection and localization. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).

2024

1. Zuo Y, Yao W, Hu Y, Fang Y, Liu W, Peng Y. Image Super-Resolution via Efficient Transformer Embedding Frequency Decomposition With Restart[J]. IEEE Transactions on Image Processing (TIP), 2024.

2. Liu W, Zhang P, Qin H, et al. Fast Image Smoothing via Quasi Weighted Least Squares.[J]. International Journal of Computer Vision (IJCV), 2024.

3. Fu, Y., Zhu, X., Li, X., Wang, X., Wu, X., Hu, S., ... & Liu, W.* (2024). Vb-kgn: Variational bayesian kernel generation networks for motion image deblurring. IEEE Transactions on Multimedia (TMM).

4. Wang, J., Liu, Z., Meng, Q., Yan, L., Wang, K., Yang, J., ... Liu, W., Hou, Q., & Cheng, M. M. (2024). Opus: occupancy prediction using a sparse set. Advances in Neural Information Processing Systems (NeurIPS), 37, 119861-119885.

2023

1. Deng, X., Zhang, P., Liu, W., & Lu, H.. Recurrent multi-scale transformer for high-resolution salient object detection[C]. In Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), 2023,7413-7423.

2. Gao, Y., Liu, J., Xu, Z., Wu, T., Zhang, E., Li, K., ...Liu W.*, & Sun, X. Softclip: Softer cross-modal alignment makes clip stronger [C]. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023,1860-1868.

3. Liu, J., Kong, L., Yang, J.*, & Liu, W.*. Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation [J]. IEEE Robotics and Automation Letters (RAL), 9(1), 763-770, 2023.

4. Chen, Y., Wei, P., Liu, Z., Wang, B., Yang, J.*, & Liu, W.* (2023). Fastc: A fast attentional framework for semantic traversability classification using point cloud. In European Conference on Artificial Intelligence (ECAI) (pp. 429-436). IOS Press.

2022及以前

1. Liu W, Zhang P, Lei Y, et al. A generalized framework for edge-preserving and structure-preserving image smoothing[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(10): 6631-6648, 2022.

2. Liu W, Zhang P, Lei Y, et al. A Generalized Framework for Edge-Preserving and Structure-Preserving Image Smoothing[C]//Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2020, 34(07): 11620-11628.

3. Liu W, Zhang P, Huang X, et al. Real-time image smoothing via iterative least squares[J]. ACM Transactions on Graphics (TOG), 2020, 39(3): 1 -24.

4. Liu W, Zhang P, Chen X, et al. Embedding bilateral filter in least squares for efficient edge-preserving image smoothing[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018, 30(1): 23-35.

5. Liu W, Chen X, Yang J, et al. Robust color guided depth map restoration[J]. IEEE Transactions on Image Processing (TIP), 2017, 26(1): 315-327.

6. Liu W, Chen X, Shen C, et al. Semi-global weighted least squares in image filtering[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2017: 5861-5869.

7. Liu W, Chen X, Yang J, et al. Variable bandwidth weighting for texture copy artifact suppression in guided depth upsampling[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017, 27(10): 2072-2085.

8. Liu W, Jia S, Li P, et al. An MRF-based depth upsampling: Upsample the depth map with its own property[J]. IEEE Signal Processing Letters (SPL), 2015, 22(10): 1708-1712.

9. Liu W, Chen X, Yang J, et al. Robust weighted least squares for guided depth upsampling[C]//IEEE International Conference on Image Processing (ICIP), 2016: 559-563.

10. Liu W, Li P, Yang J, et al. Upsampling the depth map with its own properties[C]//IEEE International Conference on Image Processing (ICIP). IEEE, 2015: 3530-3534.

11. Zhang P, Liu W, Zeng Y, et al. Looking for the detail and context devils: High-resolution salient object detection[J]. IEEE Transactions on Image Processing（TIP）, 2021, 30: 3204-3216.

12. Zhang P, Liu W, Lei Y, et al. RAPNet: Residual atrous pyramid network for importance-aware street scene parsing[J]. IEEE Transactions on Image Processing（TIP）, 2020, 29: 5010-5021.

13. Zhang P, Liu W, Lei Y, et al. Deep multiphase level set for scene parsing[J]. IEEE Transactions on Image Processing（TIP） 2020, 29: 4556-4567.

14. Zhang P, Liu W, Lu H, et al. Salient object detection with lossless feature reflection and weighted structural loss[J]. IEEE Transactions on Image Processing（TIP）, 2019, 28(6): 3048-3060.

15. Zhang P, Liu W, Lei Y, et al. Cascaded context pyramid for full-resolution 3D semantic scene completion[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision（ICCV）.

16. Zhang P, Liu W, Lu H, et al. Salient object detection by lossless feature reflection[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence（IJCAI）. 2018: 1149-1155.

17. Zhang P, Liu W, Lei Y, et al. Semantic scene labeling via deep nested level set[J]. IEEE Transactions on Intelligent Transportation Systems（TITS）, 2020, 22(11): 6853-6865.

18. Zhang P, Liu W, Wang D, et al. Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps[J]. Pattern Recognition（PR）, 2020, 100: 107130.

19. Zhang P, Liu W, Lei Y, et al. Hyperfusion-Net: Hyper-densely reflective feature fusion for salient object detection[J]. Pattern Recognition（PR）, 2019, 93: 521-533. 

20. Zhang P, Liu W, Wang H, et al. Deep gated attention networks for large-scale street-level scene segmentation[J]. Pattern Recognition（PR）, 2019, 88: 702-714.

上海交通大学“十佳班主任”（提名奖），2025

本科生国家自然科学基金导师，2024

国家高层次青年人才，2023

上海市海外高层次人才，2023

上海市浦江人才， 2022

• IEEE Transactions on Image Processing 期刊编委（Associate Editor）