Computer Vision Group, Albert-Ludwigs-Universität Freiburg

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 Estimatio...

lmb-freiburg

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

lmb-freiburg

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

lmb-freiburg

Repository for the Robust Multi-View Depth Benchmark

lmb-freiburg

Unsupervised Generation of a Viewpoint Annotated Car Dataset from Videos

lmb-freiburg

What Do Single-view 3D Reconstruction Networks Learn?

lmb-freiburg

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

lmb-freiburg

Localized Vision-Language Matching for Open-vocabulary Object Detection

lmb-freiburg