Scholar
Lukas Höllein
Google Scholar ID: Te0MGV4AAAAJ
PhD Student at Technical University of Munich
Citations & Impact
Citations
459
H-index
5
i10-index
5
Publications
8
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - WorldExplorer: Towards Generating Fully Navigable 3D Scenes (SIGGRAPH Asia, 2025)
- - IntrinsiX: High-Quality PBR Generation using Image Priors (NeurIPS, 2025)
- - 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt (ICCV, 2025)
- - QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization (ICCV, 2025)
- - ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR, 2024)
- - ControlRoom3D: Room Generation using Semantic Proxy Rooms (CVPR, 2024)
- - Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models (ICCV, 2023)
- - StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions (CVPR, 2022)
Research Experience
- Summer 2023: Research Scientist Intern at Meta Reality Labs in Zurich, under the guidance of Aljaž Božič.
Education
- Master's Degree: Technical University of Munich, Computer Science; Bachelor's Degree: Coburg University, Computer Science. Advisor: Prof. Dr. Matthias Nießner.
Background
- Research Interests: Intersection of computer vision/graphics and machine learning, particularly 3D reconstruction and generation; especially interested in the creation of fully navigable 3D worlds with the help of generative AI.
Miscellany
- Contact: Email, Google Scholar, Twitter, GitHub, CV
