Dave Zhenyu Chen

Hey there! I’m Dave Zhenyu Chen (in Chinese: 陈振宇).

I’m currently a PhD candidate at TUM Visual Computing Group. My interests are in the intersection between Deep Learning, 3D Computer Vision and Natural Language Processing. More specifically:

  • 3D scene understanding;
  • Grounding natural language in 3D environments;
  • Text-to-3D synthesis.

I’ve been researching full-time at Prof. Matthias Nießner’s Visual Computing Group at the Technical University of Munich for the past 4 years. I also have a close research collaboration with Prof. Angel Chang at Simon Fraser University, Canada.

Prior to the PhD, I received my Master’s Degree in Informatics at Ludwig Maximilians University of Munich (LMU).

zhenyu[dot]chen{at}tum[dot]de

Research

  1. SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors
    Dave Zhenyu Chen, Haoxuan Li, Hsin-Ying Lee, and 2 more authors
    2024
  2. Text2Tex: Text-driven Texture Synthesis via Diffusion Models
    Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
  3. UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding
    Dave Zhenyu Chen, Ronghang Hu, Xinlei Chen, and 2 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2023
  4. D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
    Dave Zhenyu Chen, Qirui Wu, Matthias Nießner, and 1 more author
    In European Conference on Computer Vision, Oct 2022
  5. Scan2Cap: Context-aware Dense Captioning in RGB-D Scans
    Dave Zhenyu ChenAli GholamiMatthias Niessner, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Oct 2021
  6. ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
    Dave Zhenyu ChenAngel X. Chang, and Matthias Niessner
    In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XX 16, Oct 2020