Primary tabs

From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality

Research thrust(s): Learning with Dynamic Data and Video

Video

Blind or no-reference (NR) perceptual picture quality prediction is a difficult, unsolved problem of great consequence to the social and streaming media industries that impacts billions of viewers daily. Unfortunately, popular NR prediction models perform poorly on real-world distorted pictures. To advance progress on this problem, we introduce the largest (by far) subjective picture quality database, containing about 40000 real-world distorted pictures and 120000 patches, on which we collected about 4M human judgments of picture quality. Using these picture and patch quality labels, we built deep region-based architectures that learn to produce state-of-the-art global picture quality predictions as well as useful local picture quality maps. Our innovations include picture quality prediction architectures that produce global-to-local inferences as well as local-to-global inferences (via feedback).

LIVE-FB Large-Scale Social Picture Quality Database

The LIVE-FB Large-Scale Social Picture Quality Database includes 39,810 images and 119,430 patches extracted from them, on which we collected about 4M quality scores in total from 7,865 unique subjects.

Exemplar pictures from the new database, each resized to fit. Actual pictures are of highly diverse sizes and shapes.
Exemplar pictures from the new database, each resized to fit. Actual pictures are of highly diverse sizes and shapes.

Examples

Spatial quality maps generated using the P2P-RM. Left: Original Images. Right: Quality maps blended with the originals using magma color.
Spatial quality maps generated using the P2P-RM. Left: Original Images. Right: Quality maps blended with the originals using magma color.

References

  1. D. Ghadiyaram and A. C. Bovik. Massive online crowdsourced study of subjective and objective picture quality. IEEE Transactions on Image Processing, vol. 25, no. 1, pp. 372-387, Jan 2016. 2, 3, 4, 5, 8, 12
  2. Z. Ying, M. Mandal, D. Ghadiyaram, and A. Bovik, "PatchVQ:'patching up' the video quality problem, arXiv preprint arXiv:2011.13544, 2020.
  3. D. Ghadiyaram and A. C. Bovik. Perceptual quality prediction on authentically distorted images using a bag of features approach. Journal of Vision, vol. 17, no. 1, art. 32, pp. 1-25, January 2017. 2
  4. H. R. Sheikh, M. F. Sabir, and A. C. Bovik. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Transactions on Image Processing, vol. 15, no. 11, pp. 3440-3451, Nov 2006. 2, 3, 4
  5. H. Lin, V. Hosu, and D. Saupe. Koniq-10K: Towards an ecologically valid and large-scale IQA database. arXiv preprint arXiv:1803.08489, March 2018. 2, 3, 4, 5, 8, 12