CompVis - Computer Vision and Learning LMU Munich
Computer Vision and Learning research group at Ludwig Maximilian University of Munich (formerly Computer Vision Group at Heidelberg University)
Germany
Pinned Repositories
adaptive-style-transfer
source code for the ECCV18 paper A Style-Aware Content Loss for Real-time HD Style Transfer
depth-fm
[AAAI 2025] DepthFM: Fast Monocular Depth Estimation with Flow Matching
geometry-free-view-synthesis
Is a geometric model required to synthesize novel views from a single image?
latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
metric-learning-divide-and-conquer
Source code for the paper "Divide and Conquer the Embedding Space for Metric Learning", CVPR 2019
net2net
Network-to-Network Translation with Conditional Invertible Neural Networks
stable-diffusion
A latent text-to-image diffusion model
taming-transformers
Taming Transformers for High-Resolution Image Synthesis
vunet
A generative model conditioned on shape and appearance.
zigma
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
CompVis - Computer Vision and Learning LMU Munich's Repositories
CompVis/stable-diffusion
A latent text-to-image diffusion model
CompVis/latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
CompVis/taming-transformers
Taming Transformers for High-Resolution Image Synthesis
CompVis/depth-fm
[AAAI 2025] DepthFM: Fast Monocular Depth Estimation with Flow Matching
CompVis/geometry-free-view-synthesis
Is a geometric model required to synthesize novel views from a single image?
CompVis/zigma
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
CompVis/fm-boosting
FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)
CompVis/net2net
Network-to-Network Translation with Conditional Invertible Neural Networks
CompVis/image2video-synthesis-using-cINNs
Implementation of Stochastic Image-to-Video Synthesis using cINNs.
CompVis/retrieval-augmented-diffusion-models
Official codebase for the Paper “Retrieval-Augmented Diffusion Models”
CompVis/imagebart
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
CompVis/attribute-control
Fine-Grained Subject-Specific Attribute Expression Control in T2I Models
CompVis/discrete-interpolants
The official implementation of "[MASK] is All You Need"
CompVis/LoRAdapter
CompVis/mask
The official implementation of "[MASK] is All You Need"
CompVis/interactive-image2video-synthesis
CompVis/ipoke
iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
CompVis/tread
CompVis/cleandift
CompVis/instant-lora-composition
CompVis/behavior-driven-video-synthesis
CompVis/metric-learning-divide-and-conquer-improved
Source code for the paper "Improving Deep Metric Learning byDivide and Conquer"
CompVis/distilldift
DistillDIFT: Distillation of Diffusion Features for Semantic Correspondence (WACV 2025)
CompVis/maskflow
MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
CompVis/cuneiform-sign-detection-dataset
Dataset provided with the article "Deep learning for cuneiform sign detection with weak supervision using transliteration alignment". It comprises image references, transliterations and sign annotations of clay tablets from the Neo-Assyrian epoch.
CompVis/DisCLIP
Does VLM Classification Benefit from LLM Description Semantics? (AAAI 2025)
CompVis/visual-search
Visual search interface
CompVis/cuneiform-sign-detection-code
Code for the article "Deep learning of cuneiform sign detection with weak supervision using transliteration alignment"
CompVis/wast3d
Official project page for the paper "WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians"
CompVis/zigma2