Datasets

Binaries/Code

Datasets

Open Source Software

		Freiburg-Berkeley Motion Segmentation Dataset			Video Segmentation Benchmark
		Image Sequences			TEM Dataset
		TILDA Textile Texture Database			Training data for Exemplar CNN
		Generated Matching Dataset			Training data for chair generation
		Stereo Ego-motion Dataset			Optical Flow Datasets: "Flying Chairs", "ChairsSDHom"
		Scene Flow Datasets			Human Part Segmentation Datasets
		Rendered Handpose Dataset			Pedestrian Zone Scene
		FreiHAND Dataset			HanCo Dataset
		Human Pose RGBD Datasets			OVAD: Open-Vocabulary Attribute Detection Dataset
		ADE-OoD: a benchmark for dense Out-of-Distribution detection on natural images.

---

Generated Matching Dataset

Terms of use

The dataset is only provided for research purposes and without any warranty. Any commercial use is prohibited. When using, you should cite the following paper:

P.Fischer, A. Dosovitskiy, T. Brox
Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT,
on arXiv(1405.5769), May 2014.

Link to dataset: Dataset download

The file also includes MATLAB code to process the ground truth of the geometric transformations. Given the coordinates in one image of a pair, they can be mapped to the other using the applyTransformationToCoords() function. Pairs are always made from the _original image and a warped image. Hence the ground truth in blur2.mat corresponds to the pair _original.jpg / blur2.jpg.