Skip to content
@IGL-HKUST

IGL-HKUST

Intelligent Graphics Lab at Hong Kong University of Science and Technology
README.md

IGL-HKUST

We are the Intelligent Graphics Lab at Hong Kong University of Science and Technology (IGL-HKUST). We focus on developing new technologies for 3D reconstruction, 3D generation, and 3D-aware video generation.

Members

Name Role Misc.
Yuan Liu Assistant Professor
Jiahao Lu PhD Student 25 Fall, Master@USTC, Bachelor@HUST
Co-supervised by Prof. Sai-Kit Yeung
Chengfeng Zhao PhD Student 25 Fall, Master@ShanghaiTech, Bachelor@ShanghaiTech
Zekai Gu PhD Student 25 Fall, Master@NUS, Bachelor@SCUT
Chengwei Ren PhD Student 25 Fall, Master@THU, Bachelor@HDU
Yingshuang Zou PhD Student 26 Spring, Master@THUSZ, Bachelor@NWPU
Yongsen Mao PhD Student 26 Spring, Master@SFU, Bachelor@SFU
Cheng Wan PhD Student 26 Fall, Bachelor@RUC
Peng Li PhD Student 23 Fall, Master@THU, Bachelor@XDU
Co-supervised by Prof. Wenhan Luo and Prof. Yike Guo

Works

Dynamic 3D Reconstruction

(CVPR'25 Highlight) Align3R: Aligned Monocular Depth Estimation for Dynamic Videos GitHub stars

3D-aware Video Generation

(SIGGRAPH'25) Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation ControlGitHub stars

3D Generation

(ICLR'24) SyncDreamer: Generating Multiview-consistent Images from a Single-view ImageGitHub stars

(CVPR'24) Wonder3D: Single Image to 3D using Cross-Domain DiffusionGitHub stars

(ECCV'24) Disentangled Clothed Avatar Generation from Text DescriptionsGitHub stars

(NeurIPS'24) Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise AttentionGitHub stars

(SIGGRAPH'24) DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion ModelsGitHub stars

(CVPR'25) PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit RemeshingGitHub stars

(SIGGRAPH'25) PDT: Point Distribution Transformation with Diffusion ModelsGitHub stars

(arXiv'25) MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global AssemblyGitHub stars

Neural Rendering & 3DGS

(NeurIPS'21 Spotlight) NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionGitHub stars

(CVPR'22) Neural Rays for Occlusion-aware Image-based RenderingGitHub stars

(CVPR'23) F2NeRF: Fast Neural Radiance Field Training with Free Camera TrajectoriesGitHub stars

(SIGGRAPH'23 ToG) NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview ImagesGitHub stars

(arXiv'24) NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

(arXiv'25) MEGS2: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning

6DoF Object Pose

(ECCV'22)Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB ImagesGitHub stars

Popular repositories Loading

  1. DiffusionAsShader DiffusionAsShader Public

    [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

    Python 775 34

  2. SyncHuman SyncHuman Public

    [NeurIPS 2025]SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.

    Jupyter Notebook 53

  3. TrackingWorld TrackingWorld Public

    [NeurIPS 25] TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

    20

  4. MEGS-2 MEGS-2 Public

    MEGS²: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning

    JavaScript 16 1

  5. UNIC UNIC Public

    Official repository of paper "UNIC: Neural Garment Deformation Field for Real-time Clothed Character Animation".

    7 1

  6. das das Public

    Diffusion as Shader: 3D-aware Controllable Video Generation

    JavaScript 2 1

Repositories

Showing 8 of 8 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…