• Songhai ZHANG

• Associate Professor

• Department of Computer Science and Technology

• Joined Department: 2009

• Email:shz@tsinghua.edu.cn

• Phone:+86-10-62797001 ext. 808

• Fax:+86-10-62797459

Education background

Bachelor of Computer Science & Technology, Tsinghua University, Beijing, China, 2001;

Master of Computer Science & Technology, Tsinghua University, Beijing, China, 2004;

Ph.D. in Computer Science & Technology, Tsinghua University, Beijing, China, 2007.

Areas of Research Interests/ Research Projects

Virtual Reality, Computer Graphics, Image/Video Processing

Research Projects

National Key R&D Program: Research and Development of Key Technologies for 3D Digital Interaction Engine and Construction of Its Application Ecosystem.

National Natural Science Foundation of China (Collaborative Program): Narrative Content Generation and Immersive Interaction of Dynamic Panoramic Video (2024-2026).

National Natural Science Foundation of China (Key Program): Panoramic vision data analysis, processing and VR interaction (2022-2026).

Research Status

The main research areas are computer graphics and virtual reality, as well as generative artificial intelligence, with specific directions including 3D content generation, 3D scene synthesis, and VR interaction. Over the past five years (since 2021), more than 40 papers have been published in CCF-A journals and conferences such as IEEE TPAMI, IEEE TVCG, IEEE TIP, ACM SIGGRAPH, CVPR, ICCV, IEEE VR, and ACM MM.

Selected Publications

[1] Song-Hai Zhang, Chia-Hao Chen, Zheng Fu, Yong-Liang Yang, Shi-Min Hu. Adaptive Optimization Algorithm for Resetting Techniques in Obstacle-ridden Environments. IEEE Transactions on Visualization and Computer Graphics. 2022. 29 (4): 2080-2092.

[2] Song-Hai Zhang, Shao-Kui Zhang, Wei-Yu Xie, Cheng-Yang Luo, Yong-Liang Yang, Hongbo Fu. Fast 3D Indoor Scene Synthesis by Learning Spatial Relation Priors of Objects. IEEE Transactions on Visualization and Computer Graphics. 2021. 28 (9): 3082-3092.

[3] Kang Chen, Zhipeng Tan, Jin Lei, Song-Hai Zhang*, Yuan-Chen Guo, Weidong Zhang, Shi-Min Hu. ChoreoMaster: Choreography-Oriented Music-Driven Dance Synthesis. ACM Transactions on Graphics (ACM Siggraph 2021). 40(4): 1-13.

[4] Song-Hai Zhang, Chiahao Chen, Stefanie Zollmann. One-step out-of-place resetting for redirected walking in VR. IEEE Transactions on Visualization and Computer Graphics. 2022. 29 (7): 3327-3339.

[5] Zi-Xin Zou, Zhipeng Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Yan-Pei Cao, Song-Hai Zhang*. Triplane meets gaussian splatting: Fast and generalizable single-view 3d reconstruction with transformers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024: 10324-10335.

[6] Yuan-Chen Guo, Yan-Pei Cao, Chen Wang, Yu He, Ying Shan, Song-Hai Zhang*. VMesh: Hybrid volume-mesh representation for efficient view synthesis. SIGGRAPH Asia 2023 Conference Papers. 2023: 1-11.

[7] Zi-Xin Zou, Weihao Cheng, Yan-Pei Cao, Shi-Sheng Huang, Ying Shan, Song-Hai Zhang*. Sparse3d: Distilling multiview-consistent diffusion for object reconstruction from sparse views[C]//Proceedings of the AAAI conference on artificial intelligence. 2024, 38(7): 7900-7908.

[8] Sen-Zhe Xu, Fiona Xiao Yu Chen, Ran Gong, Fang-Lue Zhang, Song-Hai Zhang*. BiRD: Using Bidirectional Rotation Gain Differences to Redirect Users during Back-and-forth Head Turns in Walking. IEEE Transactions on Visualization and Computer Graphics , 2024, 30(5): 2693-2702. IEEE VR 2024. DOI: 10.1109/TVCG.2024.3372094.

[9] Sen-Zhe Xu, Kui Huang, Cheng-Wei Fan, Song-Hai Zhang*. Spatial Contraction Based on Velocity Variation for Natural Walking in Virtual Reality. IEEE Transactions on Visualization and Computer Graphics 2024, 30(5): 2444-2453. IEEE VR 2024. DOI: 10.1109/TVCG.2024.3372109.

[10] Ying-Tian Liu, Jiajun Li, Yu-Tao Liu, Xin Yu, Yuan-Chen Guo, Yan-Pei Cao, Ding Liang, Ariel Shamir, Song-Hai Zhang*. NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2025.

[11] Yue-Jiang Dong, Wang Zhao, Jiale Xu, Ying Shan, Song-Hai Zhang*. DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2025.

[12] Heyi Sun, Cong Wang, Tianxing Xu, Jingwei Huang, Di Kang, Chunchao Guo, Song-Hai Zhang*. SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2025.

[13] Tian-Xing Xu, Xiangjun Gao, Wenbo Hu, Xiaoyu Li, Song-Hai Zhang*, Ying Shan. GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2025.

[14] Liang Yue, Shao-Kui Zhang, Lin Yuan, Yi-Tao Chen, ZiRui Zhou, Song-Hai Zhang*. Synthesizing 3D Scenes via Diffusion Model that Incorporates Indoor Scene Characteristics. //Proceedings of the 33nd ACM International Conference on Multimedia. 2025.

[15] Zheng Chen, Chenming Wu, Zhelun Shen, Chen Zhao, Weicai Ye, Haocheng Feng, Errui Ding, Song-Hai Zhang*. Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025 : 21590-21599.

[16] Cong Wang, Di Kang, He-Yi Sun, Shen-Han Qian, Zi-Xuan Wang, Linchao Bao, Song-Hai Zhang*. Mega: Hybrid mesh-gaussian head avatar for high-fidelity rendering and head editing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2025 : 26274-26284.

[17] Weicai Ye, Chenhao Ji, Zheng Chen, Junyao Gao, Xiaoshui Huang, Song-Hai Zhang, Wanli Ouyang, Tong He*, Cairong Zhao*, Guofeng Zhang*. DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion . Advances in Neural Information Processing Systems, 2024, 37: 1304-1332.

[18] Shao-Kui Zhang, Jia-Hong Liu, Junkai Huang, Zi-Wei Chi, Hou Tam, Yong-Liang Yang, Song-Hai Zhang*. SceneExplorer: An Interactive System for Expanding, Scheduling, and Organizing Transformable Layouts[J]. IEEE Transactions on Visualization and Computer Graphics, (Early Access)., 2024. DOI: 10.1109/TVCG.2024.3488744

[19] Jia-Hong Liu, Shao-Kui Zhang, Chuyue Zhang, Song-Hai Zhang. Controllable Procedural Generation of Landscapes[C]//Proceedings of the 32nd ACM International Conference on Multimedia. 2024: 6394-6403.

[20] Guan Luo, Tian-Xing Xu, Ying-Tian Liu, Xiao-Xiong Fan, Fang-Lue Zhang, Song-Hai Zhang*. 3D Gaussian Editing with A Single Image[C]//Proceedings of the 32nd ACM International Conference on Multimedia. 2024: 6627-6636.

[21] Shao-Kui Zhang, Hanxi Zhu, Xuebin Chen, Jinghuan Chen, Zhike Peng, Ziyang Chen, Yong-Liang Yang, Song-Hai Zhang*. ScenePhotographer: Object-Oriented Photography for Residential Scenes[C]//Proceedings of the 32nd ACM International Conference on Multimedia. 2024: 7843-7851.

[22] Shao-Kui Zhang, Junkai Huang, Liang Yue, Jia-Tong Zhang, Jia-Hong Liu, Yu-Kun Lai, Song-Hai Zhang*. SceneExpander: Real-time scene synthesis for interactive floor plan editing[C]//Proceedings of the 32nd ACM International Conference on Multimedia. 2024: 6232-6240.

[23] Zi-Xin Zou, Shi-Sheng Huang*, Yan-Pei Cao, Tai-Jiang Mu, Ying Shan, Hongbo Fu, Song-Hai Zhang*. GP-Recon: Online Monocular Neural 3D Reconstruction with Geometric Prior[J]. IEEE Transactions on Visualization and Computer Graphics, ( Early Access ) 2024. DOI: 10.1109/TVCG.2024.3413860

[24] Sen-Zhe Xu, Kui Huang, Cheng-Wei Fan, Song-Hai Zhang*. SafeRDW: Keep VR users safe when jumping using redirected walking[C]//2024 IEEE Conference Virtual Reality and 3D User Interfaces (VR). IEEE, 2024: 365-375.

[25] Yue-Jiang Dong, Yuan-Chen Guo, Ying-Tian Liu, Fang-Lue Zhang, Song-Hai Zhang*. PPEA-depth: Progressive parameter-efficient adaptation for self-supervised monocular depth estimation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(2): 1609-1617.

[26] Yunhan Yang, Yukun Huang, Xiaoyang Wu, Yuan-Chen Guo, Song-Hai Zhang, Hengshuang Zhao, Tong He, Xihui Liu*. Dreamcomposer: Controllable 3d object generation via multi-view conditions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024: 8111-8120.

[27] Ying-Tian Liu, Yuan-Chen Guo, Guan Luo, Heyi Sun, Wei Yin, Song-Hai Zhang*. Pi3d: Efficient text-to-3d generation with pseudo-image diffusion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024: 19915-19924.

[28] Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin, Yuan Liu, Zhiyang Dou, Lingjie Liu, Yuexin Ma, Song-Hai Zhang, Marc Habermann, Christian Theobalt, Wenping Wang*. Wonder3d: Single image to 3d using cross-domain diffusion[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). 2024: 9970-9980.

[29] Zheng Chen, Chen Wang, Yuan-Chen Guo, Song-Hai Zhang. Structnerf: Neural radiance fields for indoor scenes with structural hints. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(12): 15694-15705. DOI: 10.1109/TPAMI.2023.3305295.

[30] Zheng Chen, Yan-Pei Cao, Yuan-Chen Guo, Chen Wang, Ying Shan, Song-Hai Zhang. PanoGRF: Generalizable spherical radiance fields for wide-baseline panoramas[J]. Advances in Neural Information Processing Systems, 2023, 36: 6961-6985.

[31] Cong Wang, Di Kang, Yan-Pei Cao, Linchao Bao, Ying Shan, Song-Hai Zhang*. Neural point-based volumetric avatar: Surface-guided neural points for efficient and photorealistic volumetric head avatar[C]//SIGGRAPH Asia 2023 Conference Papers. 2023: 1-12.

[32] Shao-Kui Zhang, Jia-Hong Liu, Yike Li, Tianyi Xiong, Ke-Xin Ren, Hongbo Fu, Song-Hai Zhang*. Automatic generation of commercial scenes[C]//Proceedings of the 31st ACM International Conference on Multimedia. 2023: 1137-1147.

[33] Shao-Kui Zhang, Hou Tam, Yike Li, Ke-Xin Ren, Hongbo Fu, Song-Hai Zhang*. Scenedirector: Interactive scene synthesis by simultaneously editing multiple objects in real-time[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 30(8): 4558-4569. DOI: 10.1109/TVCG.2023.3268115.

[34] Cheng-Wei Fan, Sen-Zhe Xu, Peng Yu, Fang-Lue Zhang, Song-Hai Zhang*. Redirected walking based on historical user walking data[C]//2023 IEEE conference virtual reality and 3D user interfaces (VR). IEEE, 2023: 53-62.

[35] Sen-Zhe Xu, Jia-Hong Liu, Miao Wang, Fang-Lue Zhang, Song-Hai Zhang*. Multi-user redirected walking in separate physical spaces for online vr scenarios[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 30(4): 1916-1926. DOI: 10.1109/TVCG.2023.3251648.

[36] Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai, Song-Hai Zhang*. Mbptrack: Improving 3d point cloud tracking with memory networks and box priors[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023: 9911-9920.

[37] Chia-Hao Chen, Ying-Tian Liu, Zhifei Zhang, Yuan-Chen Guo, Song-Hai Zhang. Joint implicit neural representation for high-fidelity and compact vector fonts[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023: 5538-5548.

[38] Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai, Song-Hai Zhang*. CXTrack: Improving 3D point cloud tracking with contextual information[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023: 1084-1093.

[39] Ying-Tian Liu, Zhifei Zhang, Yuan-Chen Guo, Matthew Fisher, Zhaowen Wang, Song-Hai Zhang*. Dualvector: Unsupervised vector font synthesis with dual-part representation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023: 14193-14202.

[40] Shao-Kui Zhang, Hou Tam, Yi-Xiao Li, Tai-Jiang Mu, Song-Hai Zhang*. Sceneviewer: Automating residential photography in virtual environments[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 29(12): 5523-5537.

[41] Chen Wang, Xian Wu, Yuan-Chen Guo, Song-Hai Zhang, Yu-Wing Tai*, Shi-Min Hu. Nerf-sr: High quality neural radiance fields using supersampling[C]//Proceedings of the 30th ACM International Conference on Multimedia. 2022: 6445-6454.

[42] Sen-Zhe Xu, Tian-Qi Liu, Jia-Hong Liu, Stefanie Zollmann, Song-Hai Zhang. Making resets away from targets: Poi aware redirected walking[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 28(11): 3778-3787. DOI: 10.1109/TVCG.2022.3203095.

[43] Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu, Zheng-Ning Liu, Peng-Tao Jiang, Tai-Jiang Mu, Song-Hai Zhang, Ralph R. Martin, Ming-Ming Cheng, Shi-Min Hu*. Attention mechanisms in computer vision: A survey. Computational Visual Media, 2022, 8(3): 331-368.

[44] Chen Wang, Song-Hai Zhang*, Yizhuo Zhang, Stefanie Zollmann, Shi-Min Hu. On Rotation Gains Within and Beyond Perceptual Limitations for Seated VR. IEEE Transactions on Visualization and Computer Graphics. 2022. 29 (7): 3380-3391.

[45] Xiao-Nan Fang, Song-Hai Zhang*, Tao Chen, Xian Wu, Ariel Shamir, Shi-Min Hu. User-Guided Deep Human Image Matting Using Arbitrary Trimaps. IEEE Transactions on Image Processing. 2022. 31: 2040-2052.

[46] Sen-Zhe Xu, Tian Lv, Guangrong He, Chia-Hao Chen, Fang-Lue Zhang, Song-Hai Zhang*. Optimal Pose Guided Redirected Walking with Pose Score Precomputation. The IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR), Christchurch, New Zealand (Virtual Event). 2022.3.12-16.

[47] Shao-Kui Zhang, Yi-Xiao Li, Yu He, Yong-Liang Yang, Song-Hai Zhang*. MageAdd: Real-Time Interaction Simulation for Scene Synthesis. the 29th ACM International Conference on Multimedia (MM'21), Chengdu, China (Virtual Event). 2021.10.20-24.

[48] Song-Hai Zhang, Yuan-Chen Guo, Qing-Wen Gu. Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches. the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2021. 6012-6021.

[49] Yu He, Ying-Tian Liu, Song-Hai Zhang*, Yu-Kun Lai, Shi-Min Hu. Context-Consistent Generation of Indoor Virtual Environments based on Geometry Constraints. IEEE Transactions on Visualization and Computer Graphics (Early Access). 2021. 28 (12): 3986-3999.

[50] Kang Chen, Yupan Wang, Song-Hai Zhang, Sen-Zhe Xu, Weidong Zhang, Shi-Min Hu. MoCap-solver: a neural solver for optical motion capture data. ACM Transactions on Graphics (TOG). 2021. 40 (4): 1-11.