Flickr-Faces-HQ (FFHQ) consists of 70,000 high-quality PNG images at 1024×1024 resolution and contains considerable variation in terms of age, ethnicity and image background. It also has good coverage of accessories such as eyeglasses, sunglasses, hats, etc. The images were crawled from Flickr, thus inheriting all the biases of that website, and automatically aligned and cropped using dlib. Only images under permissive licenses were collected. Various automatic filters were used to prune the set, and finally Amazon Mechanical Turk was used to remove the occasional statues, paintings, or photos of photos.
418 PAPERS • 12 BENCHMARKS
SIDD is an image denoising dataset containing 30,000 noisy images from 10 scenes under different lighting conditions using five representative smartphone cameras. Ground truth images are provided along with the noisy images.
79 PAPERS • 1 BENCHMARK
Color BSD68 dataset for image denoising benchmarks is part of The Berkeley Segmentation Dataset and Benchmark. It is used for measuring image denoising algorithms performance. It contains 68 images.
45 PAPERS • 15 BENCHMARKS
Benchmarking Denoising Algorithms with Real Photographs
13 PAPERS • 1 BENCHMARK
The Fluorescence Microscopy Denoising (FMD) dataset is dedicated to Poisson-Gaussian denoising. The dataset consists of 12,000 real fluorescence microscopy images obtained with commercial confocal, two-photon, and wide-field microscopes and representative biological samples such as cells, zebrafish, and mouse brain tissues. Image averaging is used to effectively obtain ground truth images and 60,000 noisy images with different noise levels.
6 PAPERS • 2 BENCHMARKS
PolyU Dataset is a large dataset of real-world noisy images with reasonably obtained corresponding “ground truth” images. The basic idea is to capture the same and unchanged scene for many (e.g., 500) times and compute their mean image, which can be roughly taken as the “ground truth” image for the real-world noisy images. The rational of this strategy is that for each pixel, the noise is generated randomly larger or smaller than 0. Sampling the same pixel many times and computing the average value will approximate the truth pixel value and alleviate significantly the noise.
6 PAPERS • NO BENCHMARKS YET
The CRVD dataset consists of 55 groups of noisy-clean videos with ISO values ranging from 1600 to 25600.
4 PAPERS • 1 BENCHMARK
An open dataset of real photographs with real noise, from identical scenes captured with varying ISO values. Most images are taken with a Fujifilm X-T1 and XF18-55mm, other photographers are encouraged to contribute images for a more diverse crowdsourced effort.
2 PAPERS • NO BENCHMARKS YET