This is your work, valued

München, Germany

Lukas Höllein

Advanced
@lukasHoel

PhD Student @ TUM Visual Computing Group

lukashoel.github.io/

text2room. Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).

1.1k

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

295

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

279

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

141

video-streaming. Example of Video Streaming via HTTP 206 Partial Content to a Video Player

28

3rscan-triplet-dataset-toolkit. Triplet Dataset Toolkit for the 3RScan Dataset

9

novel-view-synthesis. Project in the practical course "Deep Learning in Visual Computing" at TUM

4

BlenderProc. A procedural Blender pipeline for photorealistic training image generation

2

sdfstudio. A Unified Framework for Surface Reconstruction

1

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

1