Papers › Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2

Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2

9 Dec 2017arXiv:1712.03400archive 2025-07-28

Federico Baldassarre, Diego González Morín, Lucas Rodés-Guirao

We review some of the most recent approaches to colorize gray-scale images using deep learning methods. Inspired by these, we propose a model which combines a deep Convolutional Neural Network trained from scratch with high-level features extracted from the Inception-ResNet-v2 pre-trained model. Thanks to its fully convolutional architecture, our encoder-decoder model can process images of any size and aspect ratio. Other than presenting the training results, we assess the "public acceptance" of the generated images by means of a user study. Finally, we present a carousel of applications on different types of images, such as historical photographs.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

16 repositories listed; official and paper-mentioned ones first.

baldassarreFe/deep-koalarization officialmentioned in papermentioned on GitHubtfMIT report
Chirayushya/colorization mentioned on GitHubtf report
IamShiv26/color-image mentioned on GitHubtf report
IamShiv26/sturdy-waffle mentioned on GitHubtf report
SamLynnEvans/Deep_Colorisation mentioned on GitHubpytorch report
Ye11ow-Flash/ColorIt mentioned on GitHubtf report
ahemaesh/Deep-Image-Colorization mentioned on GitHubpytorch report
bluejurand/Photos-colorization mentioned on GitHubtf report
kkhosla96/cs231n-project mentioned on GitHub report
wusize/colorization mentioned on GitHubpytorch 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

ColorizationDecoderImage Colorization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingConvolutionDropoutInception-ResNet-v2Inception-ResNet-v2 Reduction-BInception-ResNet-v2-AInception-ResNet-v2-BInception-ResNet-v2-CMax PoolingReLUReduction-AResidual ConnectionSoftmax

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