About Me
I joined Snap since 2025. Before this, I was a Research Scientist at Huawei Noah’s Ark Lab (London), and a post-doctoral researcher at TUM Visual Computing & AI Lab with Prof. Matthias Nießner. I received my Ph.D. at National Centre for Computer Animation, Bournmouth University supervised by Prof. Jian Chang and Prof. Jian J Zhang. My Ph.D. research lies in 3D Deep Learning, Computer Vision, Graphics, and focuses at 3D scene understanding, shape analysis and reconstruction. During my Ph.D., I have visited the Chinese University of Hong Kong (Shenzhen) and Shenzhen Research Institute of Big Data as a visiting researcher advised by Prof. Xiaoguang Han.
Interests
3D Computer Vision and Graphics, including
- 3D Scene Understanding & Reconstruction
- Geometric Learning & Representation
- Multi-view Geometry & Neural Rendering
- Human Agent for Embodied AI
Research Experience
- Snap Inc., London. (2025 - Present)
Generative ML/CV Engineer - Huawei Noah’s Ark Lab, London. (2023 - 2025)
Research Scientist - TUM Visual Computing Group, Germany. (April 2021 - 2023)
Post-doctoral researcher - National Centre for Computer Animation, U.K. (January 2017 - April 2021)
Ph.D. student
Topics: Content-aware indoor scene understanding and modeling
Supervisors: Prof. Jian Chang, Prof. Jian J Zhang - The Chinese University of Hong Kong (Shenzhen), China. (August 2019 - December 2020)
Visiting Ph.D. student
Topics: 3D scene understanding and reconstruction.
Project Instructor: Prof. Xiaoguang Han - State Key Laboratory of Traction Power, China. (September 2014 - December 2016)
Postgraduate researcher
Topics: Photo-based 3D modelling of train accident scenes; Data-driven vehicle dynamics simulation.
Supervisor: Zhao Tang.
Academic Services
- Conference Reviewer: CVPR’22-25, Siggraph’24-25, Siggraph Asia’24-25, ICCV’23-25, ECCV’22-24, ICLR’24, 3DV’22-25, NeurIPS’23-25, ICML’24, AAAI’24
- Journal Reviewer: TPAMI, TVCG, CGF, ISPRS, Computers & Graphics
Invited Talks and Lectures
11/2024 3D Shape Representations and AI
Invited lecture by Dr. Wenshu Zhang, University of the Arts London, London, UK
07/2024 On the Boundary of 3D Asset Reconstruction and Generation
Invited talk by Dr. Xiaofei Wu, Huawei Noah’s Ark Lab, Shenzhen
11/2023 3D Data Structures and AI
Invited lecture by Dr. Wenshu Zhang, University of the Arts London, London, UK
11/2023 Self-supervised 3D Reconstruction
Invited talk by Dr. Xiaofei Wu, Noah’s Ark Lab, Huawei, London, UK
09/2023 Towards Self-supervised 3D Scene Understanding and Reconstruction
Invited talk by Dr. Xiaoguang Han, The Chinese University of Hong Kong (Shenzhen), China
09/2023 3D Scene Understanding, Reconstruction and Generation
Invited talk by Dr. Qian Yu, Beihang University, Beijing, China
06/2023 Learning 3D Scene Priors with 2D Supervision
Poster Presentation, CVPR 2023, Vancouver, Canada
12/2022 3D Shape Reconstruction from Different Modalities
Invited talk by Dr. Kai Zhang, Southwest Jiaotong University, Chengdu, China
11/2022 3D Indoor Scene Understanding from Different Modalities
Invited talk by Dr. Shihui Guo, Xiamen University, Xiamen, China
10/2022 Pose2Room: Understanding 3D Scenes from Human Activities
Poster Presentation, ECCV 2022, Tel-Aviv, Israel
04/2022 Holistic 3D Scene Understanding from Images, Point Clouds and Human Activities
Invited talk, HiGraphics Workshop 2022, Hirschegg, Austria
06/2021 RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
Poster Presentation, CVPR 2021, Virtual
12/2020 Skeleton-bridged Point Completion: From Global Inference to Local Adjustment
Poster Presentation, NeurIPS 2020, Virtual
06/2020 Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image
Oral Presentation, CVPR 2020, Virtual
05/2018 Semantic Modelling of Indoor Scenes with Support Inference from a Single Photograph
Oral Presentation, CASA 2018, Beijing, China
Teaching
04/2021-08/2023 Advanced Deep Learning for Computer Vision, TU Munich