📂 Zhihao Liu

Hello this is Zhihao. I did my PhD from Sugiyama-Yokoya-Ishida Lab at the University of Tokyo (東京大学), advised by Prof. Naoto Yokoya. I was also affiliated with RIKEN AIP as a junior research assistant during the same period. Prior to that, I worked at the Game AI research center of Tencent (腾讯 IEG) as a graphics engineer. My interest lies at the intersection of computer graphics, geometry modeling and 3D vision.

Email: liuzh96 (at) outlook.com
GitHub  /  Bilibili  /  我的画(僕が描いた絵)

Profile Photo

📂 My Featured Software

Project Image

NEW! Automatic Modular Plant Generator

[GitHub] [Video]

Project Image

NEW! Point Cloud Tree Reconstruction

[GitHub] [Video]

Project Image

Sketch-based Tree Modeler

[GitHub] [Video]

Project Image

Low-poly Art Image Generator

[GitHub] [Video]

Project Image

SPH Fluid Simulation

[Demo Video]

  • The above are some of my featured free software (not papers), built purely on graphics algorithms in either C++ or C#.
  • They can be easily used on Windows PCs without any configuration.
  • See [More Projects] for more toolkits I developed. Feel free to download and explore! ^_^

📂 Publications

* Primary Authors
NeurIPS sym

Visual-to-Executable Procedural Reconstruction of Buildings.

Zichong Zhu, Zhihao Liu, Zhanglin Cheng.

The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS). 2026.

Core-A*, CCF-A  Accepted on Dec.29th. [PDF][GitHub]
AAAI sym

LandCraft: Designing the Structured 3D Landscapes via Text Guidance.

Zhihao Liu*, Fang Liu*, Weihao Xuan, Naoto Yokoya.

The Fortieth Annual AAAI Conference on Artificial Intelligence (AAAI). 2026.

Core-A*, CCF-A  [PDF] [GitHub] [Demo video]
NeurIPS sym

DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Assessment.

Junjue Wang*, Weihao Xuan*, Heli Qi, Zhihao Liu, Kunyi Liu, Yuhan Wu, Hongruixuan Chen, Jian Song, Junshi Xia, Zhuo Zheng, Naoto Yokoya.

The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS). 2025.

Core A*, CCF-A  [pdf] [GitHub]
CVPR sym

Neural Hierarchical Decomposition for Single Image Plant Modeling.

Zhihao Liu, Zhanglin Cheng, Naoto Yokoya.

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR). 2025.

Core-A*, CCF-A  [pdf] [Project page] [GitHub]
CHI sym

DeepTreeSketch: Neural Graph Prediction for Faithful 3D Tree Modeling from Sketches.

Zhihao Liu, Yu Li, Fangyuan Tu, Ruiyuan Zhang, Zhanglin Cheng, Naoto Yokoya.

ACM CHI conference on Human Factors in Computing Systems (CHI). 2024.

Core-A*, CCF-A  [pdf] [video1] [video2] [GitHub]
CVPR sym

SVDTree: Semantic Voxel Diffusion for 3D Tree Generation.

Yuan Li*, Zhihao Liu* (equal contribution), Bedrich Benes, Xiaopeng Zhang, Jianwei Guo.

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR). 2024.

Core-A*, CCF-A  [pdf] [suppl] [GitHub]
CGF sym

VRTree: Example-Based 3D Interactive Tree Modeling in Virtual Reality.

Di Wu, Mingxin Yang, Zhihao Liu, Fangyuan Tu, F. Liu, Zhanglin Cheng.

Computer Graphics Forum (CGF). 2023.

CCF-B Journal.  [pdf]
ISMAR sym

BuildingSketch: Freehand Mid-Air Sketching for Building Modeling.

Zhihao Liu, Fanxing Zhang, Zhanglin Cheng.

IEEE International Symposium on Mixed and Augmented Reality (ISMAR). 2021.

Core-A*, CCF-B  [pdf] [video] [GitHub]
VR sym

Mid-Air Finger Sketching for Tree Modeling.

F. Zhang*, Zhihao Liu* (equal contribution), Z. Cheng, Oliver Deussen, Baoquan Chen, Yunhai Wang.

IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR). 2021.

Core-A*, CCF-A  [pdf] [video] [GitHub]
GMOD sym

Single Image Tree Reconstruction via Adversarial Network.

Zhihao Liu, Kai Wu, Jianwei Guo, Yunhai Wang, Oliver Deussen, Zhanglin Cheng.

Graphical Models. 2021.

CCF-B Journal  [pdf] [video] [GitHub]
ICVRV sym

Interactive Modeling of Trees using VR Devices.

Zhihao Liu, Ce Shen, Zhi Li, Tingyu Weng, Oliver Deussen, Zhanglin Cheng, Dangxiao Wang.

IEEE International Conference on Virtual Reality and Visualization. 2019.

CCF-C Conf.  [pdf] [GitHub]

🥇 Employment

Profile Photo

Tencent Technology Ltd.      2021.
I was a graphics engineer at Game AI & Digital Content Research Center, Tencent IEG (腾讯IEG 游戏AI研究中心), developing techniques on facial motion capture for video games.