CVLGIVMay 25, 2022

Image Colorization using U-Net with Skip Connections and Fusion Layer on Landscape Images

arXiv:2205.12867v12 citationsh-index: 16
Originality Incremental advance
AI Analysis

This work addresses the problem of generating realistic color images from grayscale inputs for applications in photography and digital restoration, though it appears incremental as it builds on existing U-Net architectures.

The paper tackles automatic colorization of grayscale landscape images by combining a U-Net model with a Fusion Layer, resulting in visually more compelling colorization as validated by a user study and improvements over state-of-the-art methods.

We present a novel technique to automatically colorize grayscale images that combine the U-Net model and Fusion Layer features. This approach allows the model to learn the colorization of images from pre-trained U-Net. Moreover, the Fusion layer is applied to merge local information results dependent on small image patches with global priors of an entire image on each class, forming visually more compelling colorization results. Finally, we validate our approach with a user study evaluation and compare it against state-of-the-art, resulting in improvements.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes