Lukas Höllein
lukasHoel
PhD Student @ TUM Visual Computing Group
Languages
Loading contributions...
Top Repositories
Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).
3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt. (ICCV 2025)
StyleMesh optimizes a stylized texture for an indoor scene reconstruction (CVPR2022).
Example of Video Streaming via HTTP 206 Partial Content to a Video Player
Triplet Dataset Toolkit for the 3RScan Dataset
Project in the practical course "Deep Learning in Visual Computing" at TUM
Repositories
373DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt. (ICCV 2025)
Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).
[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes
StyleMesh optimizes a stylized texture for an indoor scene reconstruction (CVPR2022).
Triplet Dataset Toolkit for the 3RScan Dataset
A curated list of recent diffusion models for video generation, editing, and various other applications.
[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes
A unified framework for 3D content generation.
DepthSplat: Connecting Gaussian Splatting and Depth
CUDA accelerated rasterization of gaussian splatting
A Unified Framework for Surface Reconstruction
Example of Video Streaming via HTTP 206 Partial Content to a Video Player
Implementation of `Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data' (ICCV 2023)
Implementation of "Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision"
Tooling for the Common Objects In 3D dataset.
Is a geometric model required to synthesize novel views from a single image?
[CVPR 2022] Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image
A collaboration friendly studio for NeRFs
Project in the practical course "Deep Learning in Visual Computing" at TUM
No description provided.
No description provided.
A PyTorch port of the Neural 3D Mesh Renderer
No description provided.
Generator of Rad Names from Decent Paper Acronyms
No description provided.
No description provided.
Released code of Consistent Video Style Transfer via Relaxation and Regularization, TIP 2020
Adversarial Texture Optimization from RGB-D Scans (CVPR 2020).
This is the Pytorch implementation of "Learning Linear Transformations for Fast Image and Video Style Transfer" (CVPR 2019).
Implementation of Neural Style Transfer in Pytorch