Jiale Xu

Senior Researcher @ Tencent ARC Lab.

prof_pic.jpg

I am currently a senior researcher at Tencent ARC Lab, working on 3D Generative AI. I obtained my Ph.D degree at ShanghaiTech University in 2024, advised by 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, working closely with Xintao Wang and Yan-Pei Cao.

My research interests are 3D reconstruction and generation, with the goal of providing high-fidelity 3D digitization and ready-to-use 3D contents.

If you are interested in research intern opportunities or collaborations, feel free to drop me an email.

News

Jun 26, 2025 Two papers (FreeSplatter and DepthSync) are accepted by ICCV 2025.
Feb 26, 2025 Two papers (DI-PCG and NVComposer) are accepted by CVPR 2025.
Jul 19, 2024 I join Tencent ARC Lab as a senior researcher.

Selected Publications

  1. arXiv
    arxiv2025_assembler.png
    Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion
    arXiv preprint arXiv:2506.17074, 2025
  2. ICCV 2025
    iccv2025_depthsync.jpg
    DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation
    arXiv preprint arXiv:2507.01603, 2025
  3. ICCV 2025
    iccv2025_freesplatter.gif
    FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction
    Jiale Xu, Shenghua Gao, and Ying Shan
    arXiv preprint arXiv:2412.09573, 2024
  4. CVPR 2025
    cvpr2025_nvcomposer.gif
    NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images
    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025
  5. 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
  6. arXiv
    arxiv2024_instantmesh.gif
    InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
    arXiv preprint arXiv:2404.07191, 2024
  7. ECCV 2024
    eccv2024_mesh.jpeg
    MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis
    In European Conference on Computer Vision, 2024
  8. 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
  9. ECCV 2022
    eccv2022_unif.gif
    UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation
    In European Conference on Computer Vision, 2022
  10. 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