prof_pic.jpg

Jiale Xu

Senior Research Scientist
Meshy AI

I am currently a Senior Research Scientist at Meshy AI, exploring cutting-edge technologies of 3D Generative AI. Previously, I was a Senior Researcher at Tencent ARC Lab, working on 3D reconstruction and generation.

In Jul. 2024, I obtained my Ph.D degree from the School of Information Science and Technology, ShanghaiTech University, under the supervision of Prof. Shenghua Gao. Before that, I received my Bachelor’s degree in Computer Science from Harbin Institute of Technology in 2019.

From 2022 to 2024, I was a research intern at Tencent ARC Lab, working closely with Dr. Xintao Wang and Dr. Yan-Pei Cao.

We are actively looking for full-time researchers, engineers and interns to work on 3D Generative AI at Meshy. Please feel free to reach out if you are interested.

News

[2026/08/03] The technical report of Meshy T2 is released.
[2026/07/08] Invited to give a talk at USTC Summer School 2026.
[2026/02/21] Two papers (MeshWeaver and Sculpt4D) are accepted by CVPR 2026.
[2026/01/26] Two papers (Rolling-Forcing and IC-Custom) are accepted by ICLR 2026.
[2025/11/14] I join Meshy AI as a senior research scientist.
[2025/08/20] One paper (Assembler) is accepted by SIGGRAPH ASIA 2025.
[2025/06/26] Two papers (FreeSplatter and DepthSync) are accepted by ICCV 2025.
[2025/02/26] Two papers (DI-PCG and NVComposer) are accepted by CVPR 2025.
[2024/07/19] I join Tencent ARC Lab as a senior researcher.

Selected Publications

  1. Technical Report
    meshyt2.png
    Meshy T2: Fast Native Mesh Generation with Flow Matching
    Jiale Xu*, Rendong Liang*, Yuhao Long, Siyuan Shen, Zangyueyang Xian, Zeyi Xu, and Yuanming Hu
    arXiv preprint arXiv:2607.28675, 2026
  2. CVPR 2026
    cvpr2026_meshweaver.png
    MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
    Jiale Xu, Wang Zhao, and Ying Shan
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
  3. CVPR 2026
    cvpr2026_sculpt4d.png
    Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
    Minghao Yin, Wenbo Hu, Jiale Xu, Ying Shan, and Kai Han
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
  4. ICLR 2026
    arxiv2025_rolling.gif
    Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
    In The Fourteenth International Conference on Learning Representations, 2026
  5. SIGGRAPH ASIA 2025
    siggraphasia2025_assembler.png
    Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion
    In Proceedings of the SIGGRAPH Asia 2025 Conference Papers, 2025
  6. ICCV 2025
    iccv2025_freesplatter.gif
    FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction
    Jiale Xu, Shenghua Gao, and Ying Shan
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
  7. ICCV 2025
    iccv2025_depthsync.png
    DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025
  8. CVPR 2025
    cvpr2025_dipcg.png
    DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation
    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025
  9. Technical Report
    arxiv2024_instantmesh.gif
    InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
    arXiv preprint arXiv:2404.07191, 2024
  10. CVPR 2023
    cvpr2023_dream3d.gif
    Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
  11. ECCV 2022
    eccv2022_unif.gif
    UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation
    In European Conference on Computer Vision, 2022
  12. CVPR 2021
    cvpr2021_layout.png
    Layout-Guided Novel View Synthesis from A Single Indoor Panorama
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021