Yong-Jin Liu

Yong-Jin Liu

Yong-Jin Liu is a tenured Full Professor with the Computer Science Department at Tsinghua University. He obtained his Ph.D. degree in 2004 from Hong Kong University of Science & Technology. His research interests include computational geometry, computer graphics, computer aided design and pattern analysis.

Posts by Collection

portfolio

publications

NURBS curve blending using extension

Recommended citation: #Yong-Jin Liu, Rong-Qi Qiu, Xiao-Hui Liang (2009) NURBS curve blending using extension. Journal of Zhejiang University SCIENCE A, Vol. 10, No. 4, pp.570-576, 2009.

Image retargeting quality assessment

Recommended citation: Yong-Jin Liu, Xi Luo, Yu-Ming Xuan, Wen-Feng Chen, Xiao-Lan Fu (2011) Image retargeting quality assessment. Computer Graphics Forum (Eurographics 2011), Vol. 30, No. 2, pp. 583-592, 2011.

User-adaptive sketch-based 3-D CAD model retrieval

Recommended citation: Yong-Jin Liu, Xi Luo, Ajay Joneja, Cui-Xia Ma, Xiao-Lan Fu, Da-Wei Song (2013) User-adaptive sketch-based 3-D CAD model retrieval. IEEE Transactions on Automation Science and Engineering, Vol. 10, No. 3, pp. 783-795, 2013.

Cylinder detection in large-scale point cloud of pipeline plant

Recommended citation: Yong-Jin Liu, Jun-Bin Zhang, Ji-Chun Hou, Ji-Cheng Ren, Wei-Qing Tang (2013) Cylinder detection in large-scale point cloud of pipeline plant. IEEE Transactions on Visualization and Computer Graphics, Vol. 19, No. 10, pp. 1700-1707, 2013.

A computational cognition model of perception, memory and judgment

Recommended citation: #Xiaolan Fu, Lian-Hong Cai, Ye Liu, Jia Jia, Wen-Feng Chen, Yi Zhang, Guo-Zhen Zhao, Yong-Jin Liu, Chang-Xu Wu (2014) A computational cognition model of perception, memory and judgment. Science China (Series F: Information Sciences), Sci China Inf Sci, Vol. 57, No. 3, Article No. 032114(1-15), 2014.

Variational Discrete Developable Surface Interpolation

Recommended citation: Wen-Yong Gong, Yong-Jin Liu*, Kai Tang and Tie-Ru Wu (2014) Variational Discrete Developable Surface Interpolation. Journal of Computing and Information Science in Engineering, Vol. 14, No. 2, Article No. 021002, 2014.

A Sketch-based Approach for Interactive Organization of Video Clips

Recommended citation: Yong-Jin Liu, Cui-Xia Ma, Qiu-Fang Fu, Xiaolan Fu, Sheng-Feng Qin, Lexing Xie (2014) A Sketch-based Approach for Interactive Organization of Video Clips. ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 11, No. 1, Article No. 2, 2014.

Recent progress in the Laplace-Beltrami operator and its applications to digital geometry processing（数字几何处理中Laplace-Beltrami算子的离散化理论与应用研究综述）

Recommended citation: Dian Fan, Yong-Jin Liu, Ying He (2015) Recent progress in the Laplace-Beltrami operator and its applications to digital geometry processing（数字几何处理中Laplace-Beltrami算子的离散化理论与应用研究综述）. Journal of Computer-Aided Design & Computer Graphics, Vol. 27, No. 4, pp.559-569, in Chinese, 2015.

Styling evolution for tight-fitting garments

Recommended citation: Tsz-Ho Kwok, Yan-Qiu Zhang, Charlie C.L. Wang*, Yong-Jin Liu*, Kai Tang (2016) Styling evolution for tight-fitting garments. IEEE Transactions on Visualization and Computer Graphics, Vol. 22, No. 5, pp. 1580-1591, 2016.

An Interactive SpiralTape Video Summarization

Recommended citation: Yong-Jin Liu, Cuixia Ma, Guozhen Zhao, Xiaolan Fu, Hongan Wang, Guozhong Dai, Lexing Xie (2016) An Interactive SpiralTape Video Summarization. IEEE Transactions on Multimedia, Vol. 18, No. 7, pp. 1-14, 2016.

Solving the initial value problem of discrete geodesics

Recommended citation: Peng Cheng, Chunyan Miao, Yong-Jin Liu, Changhe Tu, Ying He (2016) Solving the initial value problem of discrete geodesics. Computer-Aided Design (Special issue of SPM 2015), vol. 70, pp. 144-152, 2016.

Delta DLP 3D Printing with Large Size

Recommended citation: Chenming Wu, Ran Yi, Yong-Jin Liu*, Ying He, Charlie C.L. Wang (2016). Delta DLP 3D Printing with Large Size. The 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016), pp. 2155-2160, 2016.

Cross Section based Hollowing and Structural Enhancement

Recommended citation: Weiming Wang, Baojun Li, Sicheng Qian, Yong-Jin Liu, Charlie C.L. Wang, Ligang Liu, Baocai Yin, Xiuping Liu (2017) Cross Section based Hollowing and Structural Enhancement. The Visual Computer (CGI 2017), Vol. 33, No. 6, pp. 949-960, 2017.

Delta DLP 3D Printing of Large Model

Recommended citation: Ran Yi, Chenming Wu, Yong-Jin Liu*, Ying He, Charlie C. L. Wang (2018) Delta DLP 3D Printing of Large Model. IEEE Transactions on Automation Science and Engineering, Vol. 15, No. 3, pp. 1193-1204, 2018.

Support-Free Hollowing

Recommended citation: Weiming Wang, Yong-Jin Liu, Jun Wu, Shengjing Tian, Charlie C.L. Wang, Ligang Liu, Xiuping Liu. Support-Free Hollowing. IEEE Transactions on Visualization and Computer Graphics, Vol. 24, No. 10, pp. 2787-2798, 2018.

Poisson Vector Graphics (PVG)

Recommended citation: Fei Hou, Qian Sun, Zheng Fang, Yong-Jin Liu, Shi-Min Hu, Hong Qin, Aimin Hao, Ying He. Poisson Vector Graphics (PVG). IEEE Transactions on Visualization and Computer Graphics, Vol. 26, No. 2, pp. 1361-1371, 2020.

Decorating 3D Models with Poisson Vector Graphics

Recommended citation: Qian Fu, Fei Hou, Qian Sun, Shi-Qing Xin, Yong-Jin Liu, Wencheng Wang, Hong Qin, Ying He. Decorating 3D Models with Poisson Vector Graphics. Computer-Aided Design, Vol. 102, pp. 1-18, 2018.

Evaluation on the Compactness of Supervoxels

Recommended citation: Ran Yi, Yong-Jin Liu, Yu-Kun Lai. Evaluation on the Compactness of Supervoxels. IEEE International Conference on Image Processing (ICIP 18), pp. 2212-2216, 2018.

Support-Free Volume Printing by Multi-Axis Motion

Recommended citation: Chengkai Dai, Charlie C.L. Wang, Chenming Wu, Sylvain Lefebvre, Guoxin Fang, Yong-Jin Liu. Support-Free Volume Printing by Multi-Axis Motion. ACM Transactions on Graphics (SIGGRAPH 2018), Vol. 37, No. 4, Article No. 134, 2018.

LineUp: Computing Chain-based Physical Transformation

Recommended citation: Minjing Yu, Zipeng Ye, Yong-Jin Liu*, Ying He, Charlie C.L. Wang. LineUp: Computing Chain-based Physical Transformation. ACM Transactions on Graphics (To be presented at ACM SIGGRAPH 2019), Vol. 38, No. 1, Article No. 11, 2019.

Energy-Efficient Coverage Path Planning for General Terrain Surfaces

Recommended citation: Chenming Wu, Chengkai Dai, Xiaoxi Gong, Yong-Jin Liu, Jun Wang, Xianfeng Gu, Charlie C.L. Wang. Energy-Efficient Coverage Path Planning for General Terrain Surfaces. The 2019 International Conference on Robotics and Automation (ICRA 2019), also published in IEEE Robotics and Automation Letters, Vol. 4, No. 3, pp. 2584-2591 (joint submission to ICRA 2019 and RAL).

Attention-aware Multi-stroke Style Transfer

Recommended citation: Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu and Jun Wang. Attention-aware Multi-stroke Style Transfer. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 19), pages 1467-1475, 2019.

Poisson Vector Graphics PVG-Guided Face Color Transfer in Videos

Recommended citation: Qian Fu, Ying He, Fei Hou, Qian Sun, Anxiang Zeng, Zhenchuan Huang, Juyong Zhang, Yong-Jin Liu. Poisson Vector Graphics (PVG)-Guided Face Color Transfer in Videos. IEEE Computer Graphics and Applications, vol. 41, no. 6, pp. 152-163, 1 Nov.-Dec. 2021.

Multi-target Positive Emotion Recognition from EEG Signals

Recommended citation: Guozhen Zhao, Yulin Zhang, Guanhua Zhang, Dan Zhang, Yong-Jin Liu*. Multi-target Positive Emotion Recognition from EEG Signals. IEEE Transactions on Affective Computing, DOI (identifier) 10.1109/TAFFC.2020.3043135, 2021.

GAN-based Multi-Style Photo Cartoonization

Recommended citation: Yezhi Shu, Ran Yi, Mengfei Xia, Zipeng Ye, Wang Zhao, Yang Chen, Yu-Kun Lai, Yong-Jin Liu*. GAN-based Multi-Style Photo Cartoonization. IEEE Transactions on Visualization and Computer Graphics, DOI (identifier) 10.1109/TVCG.2021.3067201, 2021.

Autoregressive Stylized Motion Synthesis with Generative Flow

Recommended citation: Yu-Hui Wen, Zhipeng Yang, Hongbo Fu, Lin Gao, Yanan Sun, Yong-Jin Liu*. Autoregressive Stylized Motion Synthesis with Generative Flow. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 21), pages 13612-13621, 2021.

Adversarial attack and interpretability of the deep neural network from the geometric perspective(几何视角下深度神经网络的对抗攻击与可解释性研究进展)

Recommended citation: Mengfei Xia, Zipeng Ye, Wang Zhao, Ran Yi, Yong-Jin Liu*. Adversarial attack and interpretability of the deep neural network from the geometric perspective(几何视角下深度神经网络的对抗攻击与可解释性研究进展). Scientia Sinica Informationis, Vol. 51, No. 9, pp.1411-1437, in Chinese, 2021.

SketchMaker: Sketch Extraction and Reuse for Interactive Scence Sketch Composition

Recommended citation: Fang Liu, Xiaoming Deng, Jiancheng Song, Yu-Kun Lai, Yong-Jin Liu*, Hao Wang, Cuixia Ma, Shengfeng Qin, and Hongan Wang. 2022. SketchMaker: Sketch Extraction and Reuse for Interactive Scene Sketch Composition. ACM Trans. Interact. Intell. Syst. 12, 3, Article 23 (September 2022), 26 pages. https://doi.org/10.1145/3543956

Research on the Construction and Interactive Feedback of the Exhibition-hall with the Introduction of Intelligent Virtual Agent(引入智能虚拟讲解员的云展厅构建与交互反馈研究)

Recommended citation: Fang Liu, Tian Lv, Xinge Liu, Sheng Ye, Rui Guo, Lie Zhang, Cuixia Ma, Qingwei Wang, Yong-Jin Liu*. Research on the Construction and Interactive Feedback of the Exhibition-hall with the Introduction of Intelligent Virtual Agent(引入智能虚拟讲解员的云展厅构建与交互反馈研究). Journal of Software, in Chinese, 2022.

Audio-driven stylized Gesture generation with flow-based model

Recommended citation: Sheng Ye, Yu-Hui Wen, Yanan Sun, Ying He, Ziyang Zhang, Yaoyuan Wang, Weihua He, and Yong-Jin Liu*. Audio-Driven Stylized Gesture Generation with Flow-Based Model. Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part V. Cham: Springer Nature Switzerland, 2022: 712-728.

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Recommended citation: Aihua Mao, Zihui Du, Yu-hui Wen*, Jun Xuan, Yong-Jin Liu*. PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows. Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III. Cham: Springer Nature Switzerland, 2022: 398-415.

A Mixture of Surprises for Unsupervised Reinforcement Learning

Recommended citation: Andrew Zhao, Matthieu Gaetan Lin, Yangguang Li, Yong-Jin Liu*, Gao Huang*. A Mixture of Surprises for Unsupervised Reinforcement Learning. Neural Information Processing Systems (NeurIPS) 2022, https://doi.org/10.48550/arXiv.2210.06702

Keyframe Control of Music-driven 3D Dance Generation

Recommended citation: Zhipeng Yang, Yu-Hui Wen, Shu-Yu Chen, Xiao Liu, Yuan Gao, Yong-Jin Liu, Lin Gao, Hongbo Fu. Keyframe Control of Music-driven 3D Dance Generation. In: IEEE Transactions on Visualization and Computer Graphics. 2023.

MSL-Net_Sharp_Feature_Detection_Network_for_3D_Point_Clouds

Recommended citation: Xianhe Jiao, Chenlei Lv, Ran Yi, Junli Zhao,Zhenkuan Pan, Zhongke Wu, Yong-Jin Liu*.MSL-Net: Sharp Feature Detection Network for 3D Point Clouds. IEEE Transactions on Visualization and Computer Graphics,PP (2023): n. pag. doi: 10.1109/TVCG.2023.3346907.

SD-FSOD Self-Distillation Paradigm via Distribution Calibration for Few-Shot Object Detection

Recommended citation: Han Chen, Qi Wang, Kailin Xie, Liang Lei, Matthieu Gaetan Lin, Tian lv, Yong-Jin Liu*, Jiebo Luo.SD-FSOD: Self-Distillation Paradigm via Distribution Calibration for Few-Shot Object Detection. IEEE Transactions on Circuits and Systems for Video Technology,Volume: 34, Issue: 7, On Page(s): 5963-5976,Print ISSN: 1051-8215,doi: 10.1109/TCSVT.2023.3343397.

Generating Artistic Portrait Drawings from Images

Recommended citation: Yi, R., Liu, YJ., Lai, YK., Rosin, P.L. (2024). Generating Artistic Portrait Drawings from Images. In: Lyu, Z. (eds) Applications of Generative AI. Springer, Cham. https://doi.org/10.1007/978-3-031-46238-2_22

O^2-Recon Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model

Abstract: Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion based in-painting model, to reconstruct complete surfaces for the hidden parts of objects. Specifically, we utilize a pretrained diffusion model to fill in the hidden areas of 2D images. Then we use these in-painted images to optimize a neural implicit surface representation for each instance for 3D reconstruction. Since creating the in-painting masks needed for this process is tricky, we adopt a human-in-the-loop strategy that involves very little human engagement to generate high-quality masks. Moreover, some parts of objects can be totally hidden because the videos are usually shot from limited perspectives. To ensure recovering these invisible areas, we develop a cascaded network architecture for predicting signed distance field, making use of different frequency bands of positional encoding and maintaining overall smoothness. Besides the commonly used rendering loss, Eikonal loss, and silhouette loss, we adopt a CLIP-based semantic consistency loss to guide the surface from unseen camera angles. Experiments on ScanNet scenes show that our proposed frame work achieves state-of-the-art accuracy and completeness in object-level reconstruction from scene-level RGB-D videos.

Recommended citation: Yubin Hu, Sheng Ye, Wang Zhao, Matthieu Lin, Yuze He, Yu-Hui Wen, Ying He, Yong-Jin Liu*.O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model.AAAI 2024.

A Diffusion Model Translator for Efficient Image-to-Image Translation

Recommended citation: M. Xia, Y. Zhou, R. Yi, Y. -J. Liu and W. Wang, "A Diffusion Model Translator for Efficient Image-to-Image Translation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 10272-10283, Dec. 2024, doi: 10.1109/TPAMI.2024.3435448.

A Multimodal Dataset for Mixed Emotion Recognition

Recommended citation: Pei Yang, Niqi Liu, Xinge Liu, Yezhi Shu, Wenqi Ji, Ziqi Ren, Jenny Sheng, Minjing Yu, Ran Yi, Dan Zhang & Yong-Jin Liu. A Multimodal Dataset for Mixed Emotion Recognition. Scientific Data. 11, Article number: 847 (2024).

NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis

Abstract: This paper presents NGP-RT, a novel approach for enhancing the rendering speed of Instant-NGP to achieve real-time novel view synthesis. As a classic NeRF-based method, Instant-NGP stores implicit features in multi-level grids or hash tables and applies a shallow MLP to convert the implicit features into explicit colors and densities. Although it achieves fast training speed, there is still a lot of room for improvement in its rendering speed due to the per-point MLP executions for implicit multi-level feature aggregation, especially for real-time applications. To address this challenge, our proposed NGP-RT explicitly stores colors and densities as hash features, and leverages a lightweight attention mechanism to disambiguate the hash collisions instead of using computationally intensive MLP. At the rendering stage, NGP-RT incorporates a pre-computed occupancy distance grid into the ray marching strategy to inform the distance to the nearest occupied voxel, thereby reducing the number of marching points and global memory access. Experimental results show that on the challenging Mip-NeRF 360 dataset, NGP-RT achieves better rendering quality than previous NeRF-based methods, achieving 108 fps at 1080p resolution on a single Nvidia RTX 3090 GPU. Our approach is promising for NeRF-based real-time applications that require efficient and high-quality rendering.

Recommended citation: Yubin Hu*, Xiaoyang Guo, Yang Xiao, Jingwei Huang, Yong-Jin Liu*. NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis. ECCV 2024.

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.