Lukas Höllein lukasHoel

Highlights

• Pro

Pinned Loading

1. Our method reconstructs 3D worlds from video diffusion models using non-rigid alignment to resolve inherent 3D inconsistencies in the generated sequences.

   Python 284 30

2. Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).

   Python 1.1k 75

3. [SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes

   Python 191 14

4. ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

   Python 382 25

5. 3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt. (ICCV 2025)

   Cuda 296 19

6. StyleMesh optimizes a stylized texture for an indoor scene reconstruction (CVPR2022).

   C++ 141 8