Jiale Xu
Scholar

Jiale Xu

Google Scholar ID: SO-JS9EAAAAJ
Tencent ARC Lab
Generative Models3D Generation3D Reconstruction
Citations & Impact
All-time
Citations
658
 
H-index
8
 
i10-index
8
 
Publications
17
 
Co-authors
15
list available
Resume (English only)
Academic Achievements
  • Published multiple papers, including:
  • - Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion (arXiv, 2025)
  • - DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation (ICCV 2025)
  • - FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction (ICCV 2025)
  • - NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images (CVPR 2025)
  • - DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation (CVPR 2025)
Research Experience
  • From 2022 to 2024, worked as a research intern at Tencent, closely collaborating with Xintao Wang and Yan-Pei Cao.
Education
  • Received Bachelor’s degree in Computer Science from Harbin Institute of Technology in 2019; obtained Ph.D. degree from ShanghaiTech University in 2024, advised by Prof. Shenghua Gao.
Background
  • Currently a senior researcher at Tencent ARC Lab, working on 3D Generative AI. The goal is to provide high-fidelity 3D digitization and ready-to-use 3D contents.
Miscellany
  • Feel free to drop an email if interested in research intern opportunities or collaborations.