Hongyu Yan (阎鸿禹)

Hongyu Yan (阎鸿禹)

About Me

  • 🎓 I am currently a Ph.D. student at HKUST, supervised by Prof. Ping Tan.
  • 🏫 Previously, I received my M.S. degree from Sichuan University (SCU) (2020–2023).
  • 🔭 My research focuses on 3D foundation models (e.g., vecset/voxel-based 3D native generation, diffusion-based artist-like mesh generation).
  • 🌱 I am also exploring and deeply interested in 3D animation, specifically rigging and skinning.
  • 💼 I am expected to graduate in 2027. I’m open to collaborations and career opportunities in the 3D industry.

News

  • Three papers accepted by CVPR 26.
  • One paper accepted by 3DV 26.
  • One paper accepted by AAAI 25.
  • One paper accepted by CVPR 25.

Publications

PoseMaster

PoseMaster: A Unified 3D Native Framework for Stylized Pose Generation

Computer Vision and Pattern Recognition (CVPR), 2026

Hongyu Yan*, Kunming Luo*, Weiyu Li, Kaiyi Zhang, Yixun Liang, Jingwei Huang, Chunchao Guo, Ping Tan

Paper | Code | BibTex

ArtLLM

ArtLLM: Generating Articulated Assets via 3D LLM

Computer Vision and Pattern Recognition (CVPR), 2026

Penghao Wang, Siyuan Xie, Hongyu Yan, Xianghui Yang, Jingwei Huang, Chunchao Guo, Jiayuan Gu

Paper | Code | BibTex

UniTex

UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes

Computer Vision and Pattern Recognition (CVPR), 2026

Yixun Liang, Kunming Luo, Xiao Chen, Rui Chen, Hongyu Yan, Weiyu Li, Jiarui Liu, Ping Tan

Paper | Code | BibTex

CTR3D

CTR3D: Cross-view Token Reduction for Dense Multi-view Generation

International Conference on 3D Vision (3DV), 2026 Best paper candidate

Kunming Luo*, Hongyu Yan*, Yuan Liu, Zihao Zhang, Manyuan Zhang, Wenping Wang, Ping Tan

Paper | BibTex

Hunyuan3DOmni

Hunyuan3D Omni: AUnified Framework for Controllable Generation of 3D Assets

Technical Report, 2026

Tencent Hunyuan3D Team, Hongyu Yan

Paper | Code | BibTex

Hunyuan3D21

Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Technical Report, 2026

Tencent Hunyuan3D Team, Hongyu Yan

Paper | Code | BibTex

CraftMan3D

CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner

Computer Vision and Pattern Recognition (CVPR), 2025 Oral presentation

Weiyu Li*, Jiarui Liu*, Hongyu Yan*, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, Xiaoxiao Long

Paper | Code | BibTex

SymmCompletion

SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance

Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2025 Oral presentation

Hongyu Yan*, Zijun Li*, Kunming Luo, Li Lu, Ping Tan

Paper | Code | BibTex

FBNet

FBNet: Feedback Network for Point Cloud Completion

European Conference on Computer Vision (ECCV), 2022 Oral presentation

Xuejun Yan*, Hongyu Yan*, Jingjing Wang, Hang Du, Zhihong Wu, Di Xie, Shiliang Pu, Li Lu

Paper | BibTex

Education

Experience

  • 2024.09-2026.03, Research Intern, Tencent Hunyuan3D
  • 2022.11-2023.06, Research Intern, Megvii Research
  • 2021.09-2022.09, Research Intern, HIK Vision

Academic Services

  • Conferences: Computer Vision and Pattern Recognition (CVPR); European Conference on Computer Vision (ECCV); International Conference on Computer Vision (ICCV); Neural Information Processing Systems (NIPS); International Conference on Learning Representations (ICLR)