Bias in Automated Image Colorization: Metrics and Error Types

Frank Stapel, Floris Weers, Doina Bucur

Research output: Working paperPreprintAcademic

26 Downloads (Pure)


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.
Original languageEnglish
Publication statusPublished - 16 Feb 2022


  • cs.CV
  • 68T45
  • I.4.4


Dive into the research topics of 'Bias in Automated Image Colorization: Metrics and Error Types'. Together they form a unique fingerprint.

Cite this