Discover lmb-freiburg/PreFAct Open Source project

Network estimating 3D Handpose from single color images

1,004

hand3d

DeMoN: Depth and Motion Network

801

demon

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

574

freihand

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

382

deeptam

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

233

mv3d

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

214

rgbd-pose3d

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

198

flownet2-docker

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

158

netdef_models

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

157

ogn

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

155

orion

MATLAB

111

what3d

What Do Single-view 3D Reconstruction Networks Learn?

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

dispnet-flownet-docker

The U-Net Segmentation plugin for Fiji (ImageJ)

Unet-Segmentation

Java

robustmvd

Repository for the Robust Multi-View Depth Benchmark

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

contra-hand

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

Multimodal-Future-Prediction

A collection of tensorflow ops

lmbspecialops

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"

FLN-EPN-RPN

flow_rl

DispNet3, FlowNet3, FlowNetH, SceneFlowNet -- in Docker

netdef-docker

The U-Net Segmentation server (caffe_unet) for Docker

caffe-unet-docker

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

Contrastive-Future-Trajectory-Prediction

Localized Vision-Language Matching for Open-vocabulary Object Detection

locov

Unsupervised Generation of a Viewpoint Annotated Car Dataset from Videos

unsup-car-dataset

MATLAB

FreiPose-docker

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

Dockerfile

optical-flow-2d-data-generation

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)

autodispnet

cv-exercises

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

spr-exercises

Jupyter Notebook

td-or-not-td

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

sf2se3

ovqa

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

understanding_flow_robustness

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

neural-point-cloud-diffusion

Official repository for "Latent Diffusion Counterfactual Explanations"

ldce

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

ROS-packages

FreiPose

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

diffusion-for-ood

tfutils is a set of tools for training networks with tensorflow

tfutils

FreiCalib

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

netdef_slim

n-D Image Analysis libraries and tools

iRoCS-Toolbox

rohl

RecordTool

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

tree-planting

Official repo for the ADE-OoD benchmark.

ade-ood