Yushen LIU-School of Software, Tsinghua University

Faculty

Name: Yushen LIU

Title: Associate Professor

Email: liuyushen@tsinghua.edu.cn

Telephone: +86-10-62795455

Research Fields: 3D Computer Vision, Shape Analysis, 3D Deep Learning, Point Cloud Understanding. Information Retrieval, Cross-model Retrieval, Semantic Search. Smart Building, Building Information Modeling (BIM). Digital Geometry Processing (DGP), Computer Graphics, Computer Aided Design.

Homepage: https://yushen-liu.github.io/

Education background

2000 - 2006: Tsinghua University. Ph.D. in Computer Science and Technology.

1996 - 2000: Jilin University. B.Sc. in Mathematics.

Experience

2009 - present: School of Software at Tsinghua University, Beijing, China.

2006 - 2009: Purdue University, West Lafayette, IN, USA. Postdoctoral researcher in School of Mechanical Engineering.

Social service

Associate Editor (AE)

IEEE Transactions on Visualization and Computer Graphics (TVCG) 2025

Area Chair (AC)

Neural Information Processing Systems (NeurIPS) 2026

International Conference on Learning Representations (ICLR) 2026

International Joint Conference on Artificial Intelligence (IJCAI) 2025

Senior Program Committee (SPC)

International Joint Conference on Artificial Intelligence (IJCAI) 2021, 2023, 2024, 2025

AAAI Conference on Artificial Intelligence (AAAI) 2022, 2026

Others

Outstanding Program Committee Award (AAAI 2026)

Outstanding reviewer for Automation in Construction (2018)

Outstanding reviewer for Journal of Computational and Applied Mathematics (2018)

Research Status

NSF of China: Learning Deep Implicit Functions of 3D Point Clouds for Reconstruction (62272263), 2023.01-2026.12, PI

NSF of China: Research on Semantic-Instance Segmentation and Shape Completion for 3D Point Clouds based on Feature Representation Learning (62072268), 2021.01-2024.12, PI

National Key R&D Program of China (2018YFB0505403), 2018.05-2022.04, PI.

Deep Earth Probe and Mineral Resources Exploration-National Science and Technology Major Project (2024ZD1003405), 2024.11-2028.10, PI of sub-project.

National Key R&D Program of China (2020YFF0304100), 2020.10-2022.12, PI of sub-project.

National Key R&D Program of China (2018YFB0505403), 2018.05-2022.04, PI.

NSF of China: Studies on semantic retrieval for building information modeling (BIM) resources based on IFC (61472202), 2015.01-2018.12, PI.

NSF of China: Studies on shape matching for 3D articulated models based on metric geometry (61272229), 2013.01-2016.12, PI.

NSF of China: Study of non-rigid 3D shape retrieval (61003095), 2011.01-2013.12, PI.

National Technological Support Program for the 12th-Five-Year Plan of China (2012BAJ03B07), 2012.01-2015.09, Major Researcher.

NSF of China: China building information technology strategic research (U0970155), finished, main researcher.

Teaching Courses

《Fundamental of Programming》 (#34100063), the undergraduate course.

《Digital Geometry Processing》 (#84100272), the graduate course.

《Business Process and Asset Management》 (#84108033), the graduate course.

Honors And Awards

On 2024, "World's Top 2% Scientists" Award.

On 2019, "Tsinghua University Annual Teaching Excellence" Award.

On 2017, "Tsinghua University Excellent Award Class (Grade) Teacher" Award (the first prize).

On 2016, Highly Cited Research Award, by the journal of Advanced Engineering Informatics (the Elsevier journal), 2016. Dr. Yu-Shen Liu is the corresponding author of this paper.

On 2016, Best Student Presentation Award, at the 16th International Conference on Computing in Civil and Building Engineering (ICCCBE2016), Osaka, Japan, 2016. Dr. Yu-Shen Liu is the corresponding author of this paper, and Ge Gao is the first author.

On 2015, Best Student Paper Award, at the Proceedings of the Ninth International Conference on Computer Aided Design and Computer Graphics (CAD-CG'05), Hong Kong, China, 2005.

On 2006, Excellent Doctoral Dissertation Award of Tsinghua University in 2006.

On 2005, Intel scholarship 2005.

On 2004, Excellent Mentor Award of Tsinghua University, 2004.

Academic Achievement

Selected Publications： (* Corresponding Author, # Equal Contribution)

[1]. Junsheng Zhou#, Weiqi Zhang#, Baorui Ma, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. UDFStudio: A Unified Framework of Datasets, Benchmarks and Generative Models for Unsigned Distance Functions. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026

[2]. Wenyuan Zhang, Chunsheng Wang, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. VRP-UDF: Towards Unbiased Learning of Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026, 48(5): 5844-5861.

[3]. Qing Li, Huifang Feng*, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu*, Zhizhong Han. PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimation. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2026, 32(2): 1713-1728.

[4]. Junsheng Zhou#, Zhifan Yang#, Liang Han, Wenyuan Zhang, Kanle Shi, Shenkun Xu, Yu-Shen Liu*. 4C4D: 4 Camera 4D Gaussian Splatting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

[5]. Weiqi Zhang#, Junsheng Zhou#, Haotian Geng, Kanle Shi, Shenkun Xu, Yi Fang, Yu-Shen Liu*. GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

[6]. Takeshi Noda, Yu-Shen Liu*, Zhizhong Han. 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

[7]. Juntong Fang#, Zequn Chen#, Weiqi Zhang#, Donglin Di, Xuancheng Zhang, Chengmin Yang, Yu-Shen Liu*. MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (Highlight)

[8]. Peng Xiang, Liang Han, Hui Zhang*, Yu-Shen Liu*, Zhizhong Han. VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026, 40(13), 10969-10977.

[9]. Shengtao Li, Yudong Liu, Ge Gao*, Ming Gu, Yu-Shen Liu. I-Filtering: Implicit Filtering for Learning Neural Distance Functions from 3D Point Clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026, 48(1): 109-126.

[10]. Wenyuan Zhang#, Jimin Tang#, Weiqi Zhang, Yi Fang, Yu-Shen Liu*, Zhizhong Han. MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference. Neural Information Processing Systems (NeurIPS), 2025.

[11]. Junsheng Zhou#, Xingyu Shi#, Haichuan Song*, Yi Fang, Yu-Shen Liu*, Zhizhong Han. U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching. Neural Information Processing Systems (NeurIPS), 2025.

[12]. Qing Li, Huifang Feng, Xun Gong, Yu-Shen Liu. VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment. Neural Information Processing Systems (NeurIPS), 2025.

[13]. Chao Chen, Yu-Shen Liu*, Zhizhong Han. NeuralTPS: Learning Signed Distance Functions without Priors from Single Sparse Point Clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025, 47(1): 565-582.

[14]. Liang Han, Xu Zhang, Haichuan Song*, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

[15]. Weiqi Zhang#, Junsheng Zhou#*, Haotian Geng#, Wenyuan Zhang, Yu-Shen Liu*. GAP: Gaussianize Any Point Clouds with Text Guidance. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

[16]. Qing Li, Huifang Feng*, Xun Gong, Yu-Shen Liu. Learning Normals of Noisy Points by Local Gradient-Aware Surface Filtering. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

[17]. Wenyuan Zhang, Emily Yue-ting Jia, Junsheng Zhou, Baorui Ma, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 11317-11327. (Highlight)

[18]. Wenyuan Zhang, Yixiao Yang, Han Huang, Liang Han, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 21642-21653.

[19]. Shujuan Li, Yu-Shen Liu*, Zhizhong Han. GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 27113-27123. (Highlight)

[20]. Takeshi Noda#, Chao Chen#, Junsheng Zhou, Weiqi Zhang, Yu-Shen Liu*, Zhizhong Han. Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 22139-22149.

[21]. Chao Chen, Yu-Shen Liu*, Zhizhong Han. Sharpening Neural Implicit Functions with Frequency Consolidation Priors. The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025. (Oral)

[22]. Han Huang#, Yulun Wu#, Chao Deng, Ge Gao*, Ming Gu, Yu-Shen Liu. FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency. The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025. (Oral)

[23]. Yulun Wu#, Han Huang#, Wenyuan Zhang, Chao Deng, Ge Gao*, Ming Gu, Yu-Shen Liu. Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views. The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025. (Oral)

[24]. Qing Li, Huifang Feng, Kanle Shi, Yue Gao, Yi Fang, Yu-Shen Liu*, Zhizhong Han. Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024, 46(12): 9957-9974.

[25]. Junsheng Zhou#, Baorui Ma#, Yu-Shen Liu*, Zhizhong Han. Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024, 46(12): 8936-8953.

[26]. Junsheng Zhou#, Baorui Ma#, Shujuan Li, Yu-Shen Liu*, Yi Fang, Zhizhong Han. CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024, 46(12): 7475-7492.

[27]. Wenyuan Zhang, Yu-Shen Liu*, Zhizhong Han. Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set. Neural Information Processing Systems (NeurIPS), 2024.

[28]. Liang Han, Junsheng Zhou, Yu-Shen Liu*, Zhizhong Han. Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis. Neural Information Processing Systems (NeurIPS), 2024.

[29]. Junsheng Zhou#, Weiqi Zhang#, Yu-Shen Liu*. DiffGS: Functional Gaussian Splatting Diffusion. Neural Information Processing Systems (NeurIPS), 2024.

[30]. Junsheng Zhou, Yu-Shen Liu*, Zhizhong Han. Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly. Neural Information Processing Systems (NeurIPS), 2024.

[31]. Chao Chen, Yu-Shen Liu*, Zhizhong Han. Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors. Neural Information Processing Systems (NeurIPS), 2024.

[32]. Takeshi Noda#, Chao Chen#, Weiqi Zhang, Xinhai Liu, Yu-Shen Liu*, Zhizhong Han. MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step. Neural Information Processing Systems (NeurIPS), 2024.

[33]. Junsheng Zhou#, Weiqi Zhang#, Baorui Ma*, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[34]. Wenyuan Zhang, Kanle Shi, Yu-Shen Liu*, Zhizhong Han. Learning Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors. European Conference on Computer Vision (ECCV), 2024.

[35]. Chao Chen, Yu-Shen Liu*, Zhizhong Han. Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes. European Conference on Computer Vision (ECCV), 2024.

[36]. Shengtao Li, Ge Gao*, Yudong Liu, Ming Gu, Yu-Shen Liu. Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds. European Conference on Computer Vision (ECCV), 2024.

[37]. Baorui Ma, Yu-Shen Liu*, Matthias Zwicker, Zhizhong Han. Inferring 3D Occupancy Fields through Implicit Reasoning on Silhouette Images. ACM Multimedia (ACM MM), 2024.

[38]. Junsheng Zhou#, Jinsheng Wang#, Baorui Ma*#, Yu-Shen Liu, Tiejun Huang, Xinlong Wang*. Uni3D: Exploring Unified 3D Representation at Scale. International Conference on Learning Representations (ICLR), 2024. (Spotlight)

[39]. Shujuan Li#, Junsheng Zhou#, Baorui Ma, Yu-Shen Liu*, Zhizhong Han. Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling. AAAI Conference on Artificial Intelligence (AAAI), 2024, pp. 3181-3189.

[40]. Han Huang, Yulun Wu, Junsheng Zhou, Ge Gao*, Ming Gu, Yu-Shen Liu. NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views. AAAI Conference on Artificial Intelligence (AAAI), 2024, pp. 2312-2320.

[41]. Shengtao Li, Ge Gao*, Yudong Liu, Yu-Shen Liu, Ming Gu. GridFormer: Point-Grid Transformer for Surface Reconstruction. AAAI Conference on Artificial Intelligence (AAAI), 2024, pp. 3163-3171.

[42]. Junsheng Zhou, Xin Wen, Baorui Ma, Yu-Shen Liu*, Yue Gao, Yi Fang, Zhizhong Han. 3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds. IEEE International Conference on Robotics and Automation (ICRA), 2024.