TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/PDS-COCO

PDS-COCO

Photometrically Distorted Synthetic COCO

ImagesCustomIntroduced 2021-04-20

Photometrically Distorted Synthetic COCO (PDS-COCO) dataset is a synthetically created dataset for homography estimation learning. The idea is exactly the same as in the Synthetic COCO (S-COCO) dataset with SSD-like image distortion added at the beginning of the whole procedure: the first step involves adjusting the brightness of the image using randomly picked value δb∈U(−32,32)\delta_b \in \mathcal{U}(-32, 32)δb​∈U(−32,32). Next, contrast, saturation and hue noise is applied with the following values: δc∈U(0.5,1.5)\delta_c \in \mathcal{U}(0.5, 1.5)δc​∈U(0.5,1.5), δs∈U(0.5,1.5)\delta_s \in \mathcal{U}(0.5, 1.5)δs​∈U(0.5,1.5) and δh∈U(−18,18)\delta_h \in \mathcal{U}(-18, 18)δh​∈U(−18,18). Finally, the color channels of the image are randomly swapped with a probability of 0.50.50.5. Such a photometric distortion procedure is applied to the original image independently to create source and target candidates.

Benchmarks

Interest Point Detection/MACE

Statistics

Papers
4
Benchmarks
1

Links

Tasks

Homography EstimationInterest Point Detection