刘玉身｜清华大学｜学者主页

2026

VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors

Jimin Tang, Wenyuan Zhang, Jie Zhou, Zian Huang, Kanle Shi, Shenkun Xu, Yu-Shen Liu, Zhizhong Han

ACM SIGGRAPH Conference Papers (SIGGRAPH)

DOI

2026

VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction

Peng Xiang, Liang Han, Hui Zhang, Yu-Shen Liu, Zhizhong Han

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2026

VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction

Association for Artificial Intelligence 2026, Zhizhong Han, Liang Han, Yu-Shen Liu, Peng Xiang, Hui Zhang

Underline Science Inc.

DOI

2025

I-Filtering: Implicit Filtering for Learning Neural Distance Functions From 3D Point Clouds

Shengtao Li, Yudong Liu, Ge Gao, Ming Gu, Yu-Shen Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2025

Learning Normals of Noisy Points by Local Gradient-Aware Surface Filtering

Qing Li, Huifang Feng, Xun Gong, Yu-Shen Liu

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2025

Sharpening Neural Implicit Functions with Frequency Consolidation Priors

Chao Ping Chen, Yu-Shen Liu, Zhizhong Han

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2025

U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching

Junsheng Zhou, XingYu Shi, Haichuan Song, Yi Fang, Yu-Shen Liu, Zhizhong Han

neural information processing systems

DOI

2025

MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference

Wenyuan Zhang, Jimin Tang, Weiqi Zhang, Yi Fang, Yu-Shen Liu, Zhizhong Han

neural information processing systems

DOI

2025

VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment

Qing Li, Huifang Feng, Xun Gong, Yu-Shen Liu

neural information processing systems

DOI

2024

Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds

Shengtao Li, Ge Gao, Yudong Liu, Ming Gu, Yu-Shen Liu

Lecture notes in computer science

DOI

2024

Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling

Shujuan Li, Junsheng Zhou, Baorui Ma, Yu-Shen Liu, Zhizhong Han

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2024

GridFormer: Point-Grid Transformer for Surface Reconstruction

Shengtao Li, Ge Gao, Yudong Liu, Yu-Shen Liu, Ming Gu

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2023

Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting

Haiping Wang, Yuan Liu, Zhen Dong, Yulan Guo, Yu-Shen Liu, Wenping Wang, Bisheng Yang

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2023

MVDLite: A fast validation algorithm for Model View Definition rules

Han Liu, Ge Gao, Hehua Zhang, Yu-Shen Liu, Yan Song, Ming Gu

Advanced Engineering Informatics

DOI

2023

Modeling and validating temporal rules with semantic Petri net for digital twins

Han Liu, Xiaoyu Song B, Ge Gao, Hehua Zhang, Yu-Shen Liu, Ming Gu

Advanced Engineering Informatics

DOI

2023

KT-Net: Knowledge Transfer for Unpaired 3D Shape Completion

Zhen Xing Cao, Wenxiao Zhang, Xin Wen, Zhen Dong, Yu-Shen Liu, Xiongwu Xiao, Bisheng Yang

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2021

Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views

Zhizhong Han, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker

ACM International Conference on Multimedia (ACM MM)

DOI

2021

Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface

Baorui Ma, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker

International Conference on Machine Learning

2021

Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching

Chao Chen, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker

International Conference on Computer Vision

2020

基于属性相似性度量的BIM构件聚类

王万齐，马宝睿，李倩，卢文龙，刘玉身

《图学学报》

2020

ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences

Zhizhong Han, Chao Chen, Yu-Shen Liu, Matthias Zwicker

ACM International Conference on Multimedia (ACM MM)

DOI

2020

CF-SIS: Semantic-Instance Segmentation of 3D Point Clouds by Context Fusion with Self-Attention

Xin Wen, Zhizhong Han, Geunhyuk Youk, Yu-Shen Liu

ACM International Conference on Multimedia (ACM MM)

DOI

2019

GIS与BIM融合的研究进展与发展趋势

武鹏飞，刘玉身，谭毅，李建锋

《测绘与空间地理信息》

2019

L2G Auto-encoder

Xinhai Liu, Zhizhong Han, Xin Wen, Yu-Shen Liu, Matthias Zwicker

ACM International Conference on Multimedia (ACM MM)

DOI

2019

Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction

Zhizhong Han, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2019

3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

Zhizhong Han, Xiyang Wang, Chi‐Man Vong, Yu-Shen Liu, Matthias Zwicker, C. L. Philip Chen

International Joint Conference on Artificial Intelligence

DOI

2019

Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views

Zhizhong Han, Xinhai Liu, Yu-Shen Liu, Matthias Zwicker

International Joint Conference on Artificial Intelligence

DOI

2019

Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-Based Sequence to Sequence Network

Xinhai Liu, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2019

View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions

Zhizhong Han, Mingyang Shang, Yu-Shen Liu, Matthias Zwicker

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2019

Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences

Zhizhong Han, Mingyang Shang, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2019

Dynamically loading IFC models on a web browser based on spatial semantic partitioning

Honglei Lu, Jiaxing Wu, Yu-Shen Liu, Wanqi Wang

Visual Computing for Industry Biomedicine and Art

DOI

2018

业主BIM实施的理论体系探索与实践

武鹏飞，谭毅，胡子航，李建锋，李博，刘玉身

《科技创新与应用》

2018

深圳市建筑工务署BIM实施标准体系研究与建立

武鹏飞，谭毅，李坤碧，李建锋，李博，刘玉身

《广东土木与建筑》

2018

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

Zhizhong Han, Mingyang Shang, Zhenbao Liu, Chi‐Man Vong, Yu-Shen Liu, Matthias Zwicker, Junwei Han, C. L. Philip Chen

IEEE Transactions on Image Processing

DOI

2017

IFCdiff: A content-based automatic comparison approach for IFC files

Xin Shi, Yu-Shen Liu, Ge Gao, Ming Gu, Haijiang Li

Automation in Construction

DOI

2017

BoSCC: Bag of Spatial Context Correlations for Spatially Enhanced 3D Shape Representation

Zhizhong Han, Zhenbao Liu, Chi‐Man Vong, Yu-Shen Liu, Shuhui Bu, Junwei Han, C. L. Philip Chen

IEEE Transactions on Image Processing

DOI

2017

Enhanced Explicit Semantic Analysis for Product Model Retrieval in Construction Industry

Han Liu, Yu-Shen Liu, Pieter Pauwels, Hongling Guo, Ming Gu

IEEE Transactions on Industrial Informatics

DOI

2016

VIV: Using visible internal volume to compute junction-aware shape descriptor of 3D articulated models

Yu-Shen Liu, Hongchen Deng, Min Liu, Lianjie Gong

Neurocomputing

DOI

2015

BIMTag: Concept-based automatic semantic annotation of online BIM product resources

Ge Gao, Yu-Shen Liu, Pengpeng Lin, Meng Wang, Ming Gu, Jun‐Hai Yong

Advanced Engineering Informatics

DOI

2015

A query expansion method for retrieving online BIM resources based on Industry Foundation Classes

Ge Gao, Yu-Shen Liu, Meng Wang, Ming Gu, Jun‐Hai Yong

Automation in Construction

DOI

2014

IFCCompressor: A content-based compression algorithm for optimizing Industry Foundation Classes files

Jing Sun, Yu-Shen Liu, Ge Gao, Xiaoguang Han

Automation in Construction

DOI

2014

Junction-aware shape descriptor for 3D articulated models using local shape-radius variation

Jinlong Feng, Yu-Shen Liu, Lianjie Gong

Signal Processing

DOI

2012

Robust shape normalization of 3D articulated volumetric models

Chao Wang, Yu-Shen Liu, Min Liu, Jun‐Hai Yong, Jean‐Claude Paul

Computer-Aided Design

DOI

2012

The IFC-based path planning for 3D indoor spaces

Ya-Hong Lin, Yu-Shen Liu, Ge Gao, Xiaoguang Han, Chengyuan Lai, Ming Gu

Advanced Engineering Informatics

DOI

2012

3DMolNavi: A web-based retrieval and navigation tool for flexible molecular shape comparison

Yu-Shen Liu, Meng Wang, Jean‐Claude Paul, Karthik Ramani A

BMC Bioinformatics

DOI

2010

Surface area estimation of digitized 3D objects using quasi-Monte Carlo methods

Yu-Shen Liu, Yi Jing, Hu Zhang, Guo-Qin Zheng, Jean‐Claude Paul

Pattern Recognition

DOI

2010

Using diffusion distances for flexible molecular shape comparison

Yu-Shen Liu, Qi Li, Guo-Qin Zheng, Karthik Ramani A, William Benjamin

BMC Bioinformatics

DOI

2008

An extension on robust directed projection of points onto point clouds

Ming-Cui Du, Yu-Shen Liu

Computer-Aided Design

DOI

2006

使用拟蒙特卡罗方法计算点模型的体积

刘玉身，雍俊海，张慧，杜明翠，孙家广

《计算机辅助设计与图形学学报》

2006

Automatic least-squares projection of points onto point clouds with applications in reverse engineering

Yu-Shen Liu, Jean‐Claude Paul, Jun‐Hai Yong, Pi-Qiang Yu, Hui Zhang, Jiaguang Sun, Karthik Ramani A

Computer-Aided Design

DOI

2006

Mesh Parameterization for an Open Connected Surface without Partition

Yu-Shen Liu, Pi-Qiang Yu, Ming-Cui Du, Jun‐Hai Yong, Zhang Hui, J. Paul

International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics)

DOI

2005

A quasi-Monte Carlo method for computing areas of point-sampled surfaces

Yu-Shen Liu, Jun‐Hai Yong, Hui Zhang, Dong-ming Yan A, Jiaguang Sun

Computer-Aided Design

DOI

2005

Mesh blending

Yu-Shen Liu, Hui Zhang, Jun‐Hai Yong, Pi-Qiang Yu, Jiaguang Sun

The Visual Computer

DOI

2004

Bilateral Filter for Meshes Using New Predictor

Yu-Shen Liu, Pi-Qiang Yu, Jun‐Hai Yong, Hui Zhang, Jiaguang Sun

Lecture notes in computer science

DOI

精选作品

期刊论文

VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors

VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction

VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface Reconstruction

I-Filtering: Implicit Filtering for Learning Neural Distance Functions From 3D Point Clouds

Learning Normals of Noisy Points by Local Gradient-Aware Surface Filtering

Sharpening Neural Implicit Functions with Frequency Consolidation Priors

U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching

MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference

VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment

Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds

Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling

GridFormer: Point-Grid Transformer for Surface Reconstruction

Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting

MVDLite: A fast validation algorithm for Model View Definition rules

Modeling and validating temporal rules with semantic Petri net for digital twins

KT-Net: Knowledge Transfer for Unpaired 3D Shape Completion

Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views

Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface

Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching

基于属性相似性度量的BIM构件聚类

ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences

CF-SIS: Semantic-Instance Segmentation of 3D Point Clouds by Context Fusion with Self-Attention

GIS与BIM融合的研究进展与发展趋势

L2G Auto-encoder

Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction

3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views

Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-Based Sequence to Sequence Network

View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions

Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences

Dynamically loading IFC models on a web browser based on spatial semantic partitioning

业主BIM实施的理论体系探索与实践

深圳市建筑工务署BIM实施标准体系研究与建立

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

IFCdiff: A content-based automatic comparison approach for IFC files

BoSCC: Bag of Spatial Context Correlations for Spatially Enhanced 3D Shape Representation

Enhanced Explicit Semantic Analysis for Product Model Retrieval in Construction Industry

VIV: Using visible internal volume to compute junction-aware shape descriptor of 3D articulated models

BIMTag: Concept-based automatic semantic annotation of online BIM product resources

A query expansion method for retrieving online BIM resources based on Industry Foundation Classes

IFCCompressor: A content-based compression algorithm for optimizing Industry Foundation Classes files

Junction-aware shape descriptor for 3D articulated models using local shape-radius variation

Robust shape normalization of 3D articulated volumetric models

The IFC-based path planning for 3D indoor spaces

3DMolNavi: A web-based retrieval and navigation tool for flexible molecular shape comparison

Surface area estimation of digitized 3D objects using quasi-Monte Carlo methods

Using diffusion distances for flexible molecular shape comparison

An extension on robust directed projection of points onto point clouds

使用拟蒙特卡罗方法计算点模型的体积

Automatic least-squares projection of points onto point clouds with applications in reverse engineering

Mesh Parameterization for an Open Connected Surface without Partition

A quasi-Monte Carlo method for computing areas of point-sampled surfaces

Mesh blending

Bilateral Filter for Meshes Using New Predictor

会议论文

实体造型系统中消除自交的拔模操作

预印本

DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images

研究方向