Daxuan (č¾¾č±) Ren (ä»»)

Ph.D Student at Nanyang Technological University, Singapore

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

I am currently a Principal Software Development Engineer at Autodesk and a Ph.D. student in the College of Computing and Data Science at Nanyang Technological University (NTU), Singapore. I am supervised by Prof. Zheng Jianmin (NTU) and Prof. Cai Jianfei (Monash University). I was previously part of the Indistrial 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 represented NTU to compete with other top universities around the globe in the International Supercomputer Conference (ISC) Student Cluster Competetion in Frankfurt, Germany, and ACM/IEEE Supercomputer Conference (SC) Student Cluster Competetion 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 and past experiences include multi-view reconstruction (camera calibration, point cloud, mesh, and texture reconstruction from multi-view RGB or Kinect-RGBD), shape parsing (turning rasterized 3D data into parametric CAD shapes), differentiable rendering, and, more broadly, 3D computer vision and graphics.

News

Aug 2024 Two paper : ā€œGTA-Human: Playing for 3D Human Recovery ā€œ was accepted at TPAMI, 2024.
Jul 2024 Two paper : ā€œMcGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction ā€œ and
ā€œDifferentiable Convex Polyhedra Optimization from Multi-view Images ā€œ was accepted at ECCV 23.
Jul 2023 One paper : ā€œDNA-Rendering A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering was accepted at ICCV 23.
Feb 2023 Iā€™m joining Autodesk as a Principal Software Development Engineer focusing on large-scale 3D understanding and parametric modeling.
Sep 2022 Three Papers : ā€œExtrudeNet: Unsupervised Inverse Sketch and Extrude for Shape Parsingā€,
ā€œHuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingā€ and
ā€œMonocular 3D Object Reconstruction with GAN Inversionā€
was accepted at ECCV 22.
Dec 2021 We have released MMHuman3D: 3D Human Parametric Model Toolbox and Benchmark.
Jul 2021 Our paper ā€œCSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingā€ was accepted at ICCV 21

Publications

  1. Differentiable Convex Polyhedra Optimization from Multi-view Images
    Ren, Daxuan, Mei, Haiyi, Shi, Hezi, Zheng, Jianmin, Cai, Jianfei, and Yang, Lei
    In European Conference on Computer Vision 2024
  2. McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction
    Daxuan, Ren, Shi, Hezi, Zheng, Jianmin, and Cai, Jianfei
    2025
  3. Dna-rendering: A diverse neural actor repository for high-fidelity human-centric rendering
    Cheng, Wei, Chen, Ruixiang, Fan, Siming, Yin, Wanqi, Chen, Keyu, Cai, Zhongang, Wang, Jingbo, Gao, Yang, Yu, Zhengming, Lin, Zhengyu, and others,
    In Proceedings of the IEEE/CVF International Conference on Computer Vision 2023
  4. ExtrudeNet: Unsupervised Inverse Sketch and Extrude for Shape Parsing
    Ren, Daxuan, Zheng, Jianmin, Cai, Jianfei, Li, Jiatong, and Zhang, Junzhe
    In European Conference on Computer Vision 2022
  5. Monocular 3D Object Reconstruction with GAN Inversion
    Zhang, Junzhe, Ren, Daxuan, Cai, Zhongang, Yeo, Chai Kiat, Dai, Bo, and Loy, Chen Change
    In European Conference on Computer Vision 2022
  6. HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
    Cai, Zhongang, Ren, Daxuan, Zeng, Ailing, Lin, Zhengyu, Yu, Tao, Wang, Wenjia, Fan, Xiangyu, Gao, Yang, Yu, Yifan, Pan, Liang, and others,
    In European Conference on Computer Vision 2022
  7. Playing for 3D human recovery
    Cai, Zhongang, Zhang, Mingyuan, Ren, Jiawei, Wei, Chen, Ren, Daxuan, Li, Jiatong, Lin, Zhengyu, Zhao, Haiyu, Yi, Shuai, Yang, Lei, and others,
    arXiv preprint arXiv:2110.07588 2021
  8. CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing
    Ren, Daxuan, Zheng, Jianmin, Cai, Jianfei, Li, Jiatong, Jiang, Haiyong, Cai, Zhongang, Zhang, Junzhe, Pan, Liang, Zhang, Mingyuan, Zhao, Haiyu, and Yi, Shuai
    In International Conference on Computer Vision 2021
  9. Messytable: Instance association in multiple camera views
    Cai, Zhongang, Zhang, Junzhe, Ren, Daxuan, Yu, Cunjun, Zhao, Haiyu, Yi, Shuai, Yeo, Chai Kiat, and Loy, Chen Change
    In European Conference on Computer Vision 2020