Papers › Bias in Automated Image Colorization: Metrics and Error Types

Bias in Automated Image Colorization: Metrics and Error Types

16 Feb 2022arXiv:2202.08143archive 2025-07-28

Frank Stapel, Floris Weers, Doina Bucur

We measure the color shifts present in colorized images from the ADE20K dataset, when colorized by the automatic GAN-based DeOldify model. We introduce fine-grained local and regional bias measurements between the original and the colorized images, and observe many colorization effects. We confirm a general desaturation effect, and also provide novel observations: a shift towards the training average, a pervasive blue shift, different color shifts among image categories, and a manual categorization of colorization errors in three classes.

PaperPDFCode

Code

weersproductions/colorization-bias officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ColorizationImage Colorization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Colorization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections