Yukang (Raikkonen) Cao    操雨康

Email       LinkedIn      Github      CV (2024.10)
Twitter       Google Scholar

I am currently a Postdoctoral Research Fellow at Nanyang Technological University (NTU) Singapore, working with Prof. Ziwei Liu . Prior to this, I obtained my Ph.D degree in the Department of Computer Science, The University of Hong Kong (HKU) advised by Prof. Kwan-Yee K. Wong, and received my B.Eng from Zhejiang University in 2020 (Rank: 3/66). I am lucky to work closely with Prof. Kai Han, Dr. Yan-Pei Cao, and Dr. Liang Pan.

My research interests are in computer vision and machine learning. Specifically, 3D/4D human reconstruction and generation, human editing, 3D/4D object generation, dynamic scene reconstruction and understanding, 2D image/3D object morphing via generative model, and the modeling of the interactions among humans, objects, and scenes, etc.

profile photo

Please feel free to contact me via Email if you want to discuss any ideas or just say hi.

News
    2026-03: One paper, GS-VTON for virtual try-on, is accpeted by IJCV 2026!
    2026-01: One paper, IGGT for instance-grounded 3D semantic reconstruction, is accepted by ICLR 2026. Big congrats to Hao Li!
    2025-09: One paper, CrowdMoGen for event-driven motion generation, is accepted by IJCV 2025!
    2025-09: One paper, WuKong for 3D morphing, is accepted by NeurIPS 2025. Big congrats to Minghao!
    2025-07: We release a survey on reconstructing 4D spatial intelligence.
    2025-06: One paper, FreeMorph for training-free 2D image morphing, is accepted by ICCV 2025! More details to come.
    2025-05: We release CrowdMoGen for zero-shot collective 3D human motion generation.
    2025-03: One paper is accepted by SIGGRAPH 2025. Big congrats to Minghao!
    2025-02: Two papers (ArtiFade, AudCast) are accepted by CVPR 2025. Big congrats to Shuya and Jiazhi!
    2025-01: AvatarGO is accepted by ICLR 2025.
    2024-10: We release AvatarGO for zero-shot 4D human-object interaction generation and animation.
    2024-10: We release GS-VTON for 3D virtual try-on.
    2024-09: We release ArtiFade for generating high-quality subject from blemished images.
    2024-08: Starting my new journey in NTU, working with Prof. Ziwei!
    2024-06: We post a survey on 3D human avatar modeling.
    2024-04: I successfully defended my PhD!
    2024-02: DreamAvatar is finally accepted by CVPR 2024.
    2023-09: HeadSculpt is accepted by NeurIPS 2023.
    2023-08: Guide3D is released for transferring multi-view generated images to 3D avatars. Hope this will inspire a little bit.
    2023-06: HeadSculpt is released for 3D editable head generation from text.
    2023-04: DreamAvatar is released for 3D controllable avatar generation from text.
    2023-03: MA-NeRF for audio-driven face synthesis is accepted by ICME 2023.
    2023-02: SeSDF for 3D human reconstruction from uncalibrated image(s) is accepted by CVPR 2023.
    2022-03: JIFF for 3D human reconstruction from single image is accepted by CVPR 2022.
Previous Experiences

  • March, 2024 - Jun, 2024: Research intern at Shanghai AI Laboratory working with Dr. Liang Pan and Prof. Ziwei Liu .
  • Dec, 2022 - Jun, 2023: Research intern at Tecent PCG, ARC Lab working with Dr. Yan-Pei Cao.
  • July, 2019 - Nov, 2019: Research student at the University of Texas, Austin working with Dr. Chandrajit Bajaj.
  • Sep, 2019 - Dec, 2019: Research student at Peking University working with Dr. Dehua Xiong.
  • July, 2018 - Oct, 2018: Research student at Tsinghua University working with Dr. Zuoqiang Shi.
Publications
(*Equal contribution, #Corresponding author)
IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
Hao Li*, Zhengyu Zou*, Fangfu Liu*, Xuanyang Zhang, Fangzhou Hong, Yukang Cao, Yushi Lan, Manyuan Zhang, Gang Yu, Dingwen Zhang#, Ziwei Liu
International Conference on Learning Representations (ICLR) 2026,
[Project Website] [arxiv] [Code] [BibTeX]

Wukong’s 72 Transformations: High-fidelity 3D Morphing via Flow Models
Minghao Yin, Yukang Cao, Kai Han#
Neural Information Processing Systems (NeurIPS) 2025,
[Project Website] [arxiv] [BibTeX]

Reconstructing 4D Spatial Intelligence: A Survey
Yukang Cao, Jiahao Lu, Zhisheng Huang, Zhuowen Shen, Chengfeng Zhao, Fangzhou Hong, Zhaoxi Chen, Xin Li, Wenping Wang, Yuan Liu#, Ziwei Liu#
Preprint 2025,
[Project Website] [arxiv] [BibTeX]

FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model
Yukang Cao, Chenyang Si, Jinghao Wang, Ziwei Liu#
International Conference on Computer Vision (ICCV) 2025,
[Project Website] [arxiv] [Code] [BibTeX]

CrowdMoGen: Zero-Shot Text-Driven Collective Motion Generation
Yukang Cao*, Xinying Guo*, Mingyuan Zhang, Haozhe Xie, Chenyang Gu, Ziwei Liu#
International Journal of Computer Vision (IJCV) 2025,
[Project Website] [arxiv] [Code] [BibTeX]

Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation
Minghao Yin, Yukang Cao, Songyou Peng, Kai Han#
SIGGRAPH 2025,
[Project Website] [arxiv] [Code] [BibTeX]

AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
Jiazhi Guan, Kaisiyuan Wang, Zhiliang Xu, Quanwei Yang, Yasheng Sun, Shengyi He, Borong Liang, Yukang Cao, Yingying Li, Haocheng Feng, Errui Ding, Jingdong Wang, Youjian Zhao#, Hang Zhou#, Ziwei Liu#
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025,
[Project Website] [arxiv] [Code] [BibTeX]

AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation
Yukang Cao, Liang Pan#, Kai Han, Kwan-Yee K. Wong, Ziwei Liu#
International Conference on Learning Representations (ICLR) 2025,
[Project Website] [arxiv] [Code] [BibTeX]

GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting
Yukang Cao*, Masoud Hadi*, Liang Pan#, Ziwei Liu#
International Journal of Computer Vision (IJCV) 2026,
[Project Website] [arxiv] [Code] [BibTeX]

ArtiFade: Learning to Generate High-quality Subject from Blemished Images.
Shuya Yang*, Shaozhe Hao*, Yukang Cao#, Kwan-Yee K. Wong#
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025,
[arxiv] [BibTeX]

A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation.
Ruihe Wang*, Yukang Cao*#, Kai Han, Kwan-Yee K. Wong
Preprint, 2024
[arxiv] [BibTeX]

Guide3D: Create 3D Avatars from Text and Image Guidance.
Yukang Cao, Yan-Pei Cao, Kai Han#, Ying Shan, Kwan-Yee K. Wong
arXiv, 2023
[arxiv] [Code] [BibTeX]

HeadSculpt: Crafting 3D Head Avatars with Text
Xiao Han*, Yukang Cao*, Kai Han, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song, Tao Xiang#, Kwan-Yee K. Wong#
Neural Information Processing Systems (NeurIPS) 2023,
[Project Website] [arxiv] [Code] [BibTeX]

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models.
Yukang Cao*, Yan-Pei Cao*, Kai Han#, Ying Shan, Kwan-Yee K. Wong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024,
[Project Website] [arxiv] [Code] [BibTeX]

SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction.
Yukang Cao, Kai Han, Kwan-Yee K. Wong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023,
[Project Website] [arxiv] [Code] [BibTeX]

JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed and Human Reconstruction.
Yukang Cao, Guanying Chen, Kai Han, Wenqi Yang, Kwan-Yee K. Wong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022,
Oral Presentation
[Project Website] [arxiv] [Code] [BibTeX]

Teaching Experiences

  • [2022-2023 Fall] COMP 3270 Artificial Intelligence, Teaching Assistance (HKU)
  • [2021-2022 Fall] COMP 2396 Object-Oriented Programming and Java, Teaching Assistance (HKU)
Awards

  • HKU Presidential Scholarship (HKU-PS, Highest Distinction in Hong Kong) (2020-2024)
  • M. Braun Postgraduate Prize (2023)
  • The Arthur and Louise May Memorial Fund Scholarship (2022, 2023, 2024)
  • HK China Gas Co Ltd Postgraduate Prize (2022)
  • Y S and Christabel Lung Postgraduate Scholarship (2021)
  • China Harbor second-class scholarship (2017-2018)
  • Honorable Mention in the Mathematical Contest in Modeling (2018)
  • Zhejiang University Outstanding Second Class Scholarship (2016-2018)
  • Zhejiang Provincial Government Scholarship (Top Distinction in Zhejiang Province) (2016-2017)
Professional Activities

  • Conference Reviewer:
    • IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 -
    • Conference on International Conference on Computer Vision (ICCV), 2023 -
    • Conference on Neural Information Processing Systems (NeurIPS), 2023 -
    • ACM SIGGRAPH Asia, 2023 -
    • Pacific Graphics, 2023 -
    • Association for the Advancement of Artificial Intelligence (AAAI), 2024 -
    • International Conference on Learning Representations (ICLR), 2024 -
    • International Conference on Machine Learning (ICML), 2024 -
    • European Conference on Computer Vision (ECCV), 2024 -
    • Asian Conference on Computer Vision (ACCV), 2024 -
  • Journal Reviewer:
    • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
    • International Journal of Computer Vision (IJCV)
    • IEEE Transactions on Multimedia (TMM)
    • IEEE Transactions on Visualization and Computer Graphics (TVCG)
    • IEEE Transactions on Circuits and Systems for Video Technology (TVCST)

    		•
    Talks

    • April, 2025 at Huawei InnovWave: "Modeling Virtual Worlds: Humans, Objects, Scenes & Interactions via Generative AI"
    • Oct, 2024 at AnySyn3D: "GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting"
    • Dec, 2023 at NTU MMLab: "3D Human Modelling from Image and Text Guidance"
    • July, 2023 at GAP Lab CUHK‑Shenzhen: “Avatar‑X: Text Guided Controllable and Editable 3D Human Avatar Generation via Diffusion Models“
    • Aug, 2023 at 智东西: "Avatar‑X: Text Guided Controllable and Editable 3D Human Avatar Generation via Diffusion Models"
    Collaborating Specialists and Friends

    The website template was adapted from Guanying Chen.