Daxuan (达萱) Ren (任)

Ph.D. Principal Software Engineer @ Autodesk

  • Principal Software Engineer @ Autodesk
  • Ph.D. from NTU School of Computer Science and Engineering (SCSE)
  • Ex-Algorithm Researcher @ SenseTime Research
  • Ex-SenseTime-NTU Industrial Post-Graduate Program (IPP)
  • Email: daxuan001 [at] e.ntu.edu.sg

I am a Principal Software Development Engineer at Autodesk, focusing on large-scale 3D understanding and parametric modeling. I received my Ph.D. from the College of Computing and Data Science at Nanyang Technological University (NTU), Singapore, supervised by Prof. Zheng Jianmin (NTU) and Prof. Cai Jianfei (Monash University). I was part of the Industrial Post-Graduate Program (IPP), a joint initiative between SenseTime and NTU under the Singapore Economic Development Board (EDB).

I received my bachelor degree in Computer Science from NTU in 2018. During my undergraduate study, I was interested in High-Performance Computing (HPC) and privileged to represent NTU to compete with other top universities around the globe in the International Supercomputer Conference (ISC) Student Cluster Competition in Frankfurt, Germany, and ACM/IEEE Supercomputer Conference (SC) Student Cluster Competition in Salt Lake City, USA.

Prior to my Ph.D, I was a software engineer in Autodesk working on large-scale 3D Reconstruction Engine (Autodesk ReCap Photo) including Structure-from-Motion (SFM), Multi-View-Stereo (MVS) and Surface Reconstruction from 2017 to 2020.

My research interests include CAD modeling and parametric shape generation, shape parsing (turning rasterized 3D data into parametric CAD shapes), 3D human modeling and recovery, human-centric rendering, differentiable rendering, multi-view 3D reconstruction, and more broadly, 3D computer vision and graphics.

News

Mar 2026 Our paper “Multi-Agent CAD Code Generation” has been accepted at SIGGRAPH 2026!
Feb 2026 Our paper “Bidirectional Query-Driven Generation of Parametric CAD Sketch” has been accepted at CVPR 2026!
Oct 2025 Our demo “Digital Life Project 2 (DLP3D)” has been accepted at SIGGRAPH Asia 2025 (Real-Time Live!).
May 2025 Our paper “Learning CAD Modeling Sequences via Projection and Part Awareness” has been accepted at NeurIPS 2025!
Aug 2024 Two paper : “GTA-Human: Playing for 3D Human Recovery “ was accepted at TPAMI, 2024.
Jul 2024 Two paper : “McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction “ and
“Differentiable Convex Polyhedra Optimization from Multi-view Images “ was accepted at ECCV 23.
Jul 2023 One paper : “DNA-Rendering A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering was accepted at ICCV 23.
Feb 2023 I’m joining Autodesk as a Principal Software Development Engineer focusing on large-scale 3D understanding and parametric modeling.
Sep 2022 Three Papers : “ExtrudeNet: Unsupervised Inverse Sketch and Extrude for Shape Parsing”,
“HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling” and
“Monocular 3D Object Reconstruction with GAN Inversion”
was accepted at ECCV 22.
Dec 2021 We have released MMHuman3D: 3D Human Parametric Model Toolbox and Benchmark.

Publications

  1. Multi-Agent CAD Code Generation
    Multi-Agent CAD Code Generation
    Yang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng, and Fang Deng
    In ACM SIGGRAPH 2026
  2. Bidirectional Query-Driven Generation of Parametric CAD Sketch
    Bidirectional Query-Driven Generation of Parametric CAD Sketch
    Yang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng, and Fang Deng
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
  3. Digital Life Project 2 (DLP3D)
    Digital Life Project 2 (DLP3D)
    Zhongang Cai, Daxuan Ren, Yang Gao, Yukun Wei, Tongxi Zhou, Zhengyu Lin, Huimuk Jang, Haoyang Zeng, Chen Change Loy, Ziwei Liu, and Lei Yang
    In ACM SIGGRAPH Asia (Real-Time Live!) 2025
  4. Learning CAD Modeling Sequences via Projection and Part Awareness
    Learning CAD Modeling Sequences via Projection and Part Awareness
    Yang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng, and Fang Deng
    In Advances in Neural Information Processing Systems 2025
  5. Differentiable Convex Polyhedra Optimization from Multi-view Images
    Differentiable Convex Polyhedra Optimization from Multi-view Images
    Daxuan Ren, Haiyi Mei, Hezi Shi, Jianmin Zheng, Jianfei Cai, and Lei Yang
    In European Conference on Computer Vision 2024
  6. McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction
    McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction
    Daxuan Ren, Hezi Shi, Jianmin Zheng, and Jianfei Cai
    In European Conference on Computer Vision 2024
  7. Dna-rendering: A diverse neural actor repository for high-fidelity human-centric rendering
    Dna-rendering: A diverse neural actor repository for high-fidelity human-centric rendering
    Wei Cheng, Ruixiang Chen, Siming Fan, Wanqi Yin, Keyu Chen, Zhongang Cai, Jingbo Wang, Yang Gao, Zhengming Yu, Zhengyu Lin, and others
    In Proceedings of the IEEE/CVF International Conference on Computer Vision 2023
  8. ExtrudeNet: Unsupervised Inverse Sketch and Extrude for Shape Parsing
    ExtrudeNet: Unsupervised Inverse Sketch and Extrude for Shape Parsing
    Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, and Junzhe Zhang
    In European Conference on Computer Vision 2022
  9. Monocular 3D Object Reconstruction with GAN Inversion
    Monocular 3D Object Reconstruction with GAN Inversion
    Junzhe Zhang, Daxuan Ren, Zhongang Cai, Chai Kiat Yeo, Bo Dai, and Chen Change Loy
    In European Conference on Computer Vision 2022
  10. HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
    HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
    Zhongang Cai, Daxuan Ren, Ailing Zeng, Zhengyu Lin, Tao Yu, Wenjia Wang, Xiangyu Fan, Yang Gao, Yifan Yu, Liang Pan, and others
    In European Conference on Computer Vision 2022
  11. Playing for 3D human recovery
    Playing for 3D human recovery
    Zhongang Cai, Mingyuan Zhang, Jiawei Ren, Chen Wei, Daxuan Ren, Jiatong Li, Zhengyu Lin, Haiyu Zhao, Shuai Yi, Lei Yang, and others
    IEEE Transactions on Pattern Analysis and Machine Intelligence 2024
  12. CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
    CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
    Daxuan Ren, Jianmin Zheng, Jianfei Cai, Jiatong Li, Haiyong Jiang, Zhongang Cai, Junzhe Zhang, Liang Pan, Mingyuan Zhang, Haiyu Zhao, and Shuai Yi
    In International Conference on Computer Vision 2021
  13. Messytable: Instance association in multiple camera views
    Messytable: Instance association in multiple camera views
    Zhongang Cai, Junzhe Zhang, Daxuan Ren, Cunjun Yu, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, and Chen Change Loy
    In European Conference on Computer Vision 2020