11 datasets found

Groups: Color Constancy Formats: JSON

Filter Results
  • Color Bengal Tiger

    A fast and hardware-friendly unsupervised learning-based method that learns its parameter values from images with unknown ground-truth illumination has been proposed.
  • Cube dataset

    A new high-quality color constancy benchmark dataset with 1365 exclusively outdoor images taken with a Canon EOS 550D camera in parts of Croatia, Slovenia, and Austria during...
  • Color Tiger

    A fast and hardware-friendly unsupervised learning-based method that learns its parameter values from images with unknown ground-truth illumination has been proposed.
  • Cube+ dataset

    A new high-quality color constancy benchmark dataset with 1707 calibrated images is created, used for testing, and made publicly available.
  • INTEL-TAU dataset

    The INTEL-TAU dataset is a color constancy dataset used for testing the proposed Channel-Wise Color Constancy approach.
  • Chen et al. dataset

    The dataset from Chen et al. contains 1736 images taken from 8 different cameras, with the same scene imaged multiple times.
  • ColorChecker Dataset

    The ColorChecker dataset is widely used and reasonably large, containing 568 images from a single camera.
  • DeepIlluminance: Contextual Illuminance Estimation via Deep Neural Networks

    The proposed approach is compared with state-of-the-art methods on the reprocessed Color Checker dataset and the NUS 8-camera dataset.
  • ColorChecker Reprocessed

    The SFU Grayball 12 and the ColorChecker Reprocessed (other names: RAW dataset, 568-dataset, Gehler’s dataset) are used.
  • Grayball 12

    The SFU Grayball 12 and the ColorChecker Reprocessed (other names: RAW dataset, 568-dataset, Gehler’s dataset) are used.
  • SFU Grayball 12 and ColorChecker Reprocessed

    Two standard benchmark datasets, the SFU Grayball 12 and the ColorChecker Reprocessed (other names: RAW dataset, 568-dataset, Gehler’s dataset) are used.