SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors (CVPR, 2024)
Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV, 2023)
UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding (ICCV, 2023)
D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding (ECCV, 2022)
Scan2Cap: Context-aware Dense Captioning in RGB-D Scans (CVPR, 2021)
ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language (ECCV, 2020)
Research Experience
Has been conducting full-time research at Prof. Matthias Nießner’s Visual Computing Group at the Technical University of Munich for the past 4 years. Also has a close research collaboration with Prof. Angel Chang at Simon Fraser University, Canada.
Education
Currently a PhD candidate at the TUM Visual Computing Group. Advisor is Prof. Matthias Nießner. Prior to the PhD, received a Master's Degree in Informatics from Ludwig Maximilians University of Munich (LMU).
Background
Research interests lie at the intersection of Deep Learning, 3D Computer Vision, and Natural Language Processing. Specifically, 3D scene understanding; grounding natural language in 3D environments; text-to-3D synthesis.