Computer Vision Group, Albert-Ludwigs-Universität Freiburg ORG

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Network estimating 3D Handpose from single color images

DeMoN: Depth and Motion Network

A dataset for estimation of hand pose and shape from single color images.

DeepTAM: Deep Tracking and Mapping https://lmb.informatik.uni-freiburg.de/people/zhouh/deeptam/

Multi-view 3D Models from Single Images with a Convolutional Network

3D Human Pose Estimation in RGBD Images for Robotic Task Learning

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

Dockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)

Repository for different network models related to flow/disparity (ECCV 18)

ORION: Orientation-boosted Voxel Nets for 3D Object Recognition

Repository for the Robust Multi-View Depth Benchmark

What Do Single-view 3D Reconstruction Networks Learn?

The U-Net Segmentation plugin for Fiji (ImageJ)

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

Code in conjunction with the publication 'Contrastive Representation Learning for Hand Shape Estimation'

The official repository for the CVPR 2019 paper "Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction"

A collection of tensorflow ops

This repository contains the source code of the CVPR 2020 paper: "Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior"

No description.

The official repository of the ICCV paper "On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors"

DispNet3, FlowNet3, FlowNetH, SceneFlowNet -- in Docker

No description.

The U-Net Segmentation server (caffe_unet) for Docker

Official code for the paper "Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models" (ICLR 2025 Oral)

Localized Vision-Language Matching for Open-vocabulary Object Detection

No description.

Official repository for "Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation"

Unsupervised Generation of a Viewpoint Annotated Car Dataset from Videos

Source code for the Orbis2 model.

FreiPose: A Deep Learning Framework for Precise Animal Motion Capture in 3D Spaces

Caffe(v1)-compatible codebase to generate optical flow training data on-the-fly; used for the IJCV 2018 paper "What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?" (http://dx.doi.org/10.1007/s11263-018-1082-6)

Code for AutoDispNet (ICCV 2019)

No description.

Official repository for "Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond". Coming soon.

Official code for the paper: "Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer" (ICLR 2026)

Official repository for "Latent Diffusion Counterfactual Explanations"

Repository for SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection

Code for the paper "TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning", Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun and Thomas Brox, ICLR 2018

EntityNet: Using Knowledge Graphs to harvest datasets for efficient CLIP model training

Official repository for "Towards Understanding Adversarial Robustness of Optical Flow Networks" (CVPR 2022)

Code and Models for the paper "Learning Representations for Predicting Future Activities"

Official code for the paper "Selective Concept Bottleneck Models Without Predefined Concepts" (TMLR 2025)

A collection of ROS packages for LMB software; DispNet(1+3), FlowNet2, etc.

No description.

Official repository for "Climate-sensitive Urban Planning Through Optimization of Tree Placements"

No description.

tfutils is a set of tools for training networks with tensorflow

A python wrapper for tf to ease creation of network definitions.

n-D Image Analysis libraries and tools

No description.

No description.

No description.

Repository containing the code for the Statistical Pattern Recognition exercises.

No description.

What Drives Compositional Generalization in Visual Generative Models?

Official code for the paper: "When and How Does CLIP Enable Domain and Compositional Generalization?" (ICML 2025 Spotlight)

Official repo for the ADE-OoD benchmark.

This is the repository that contains source code for the Hiera-Orbis website.

Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models

No description.

evaluation code for motion boundaries