Super-attention for exemplar-based image colorization

Hernan Carrillo, Michaël Clément, Aurelie Bugeau; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 4548-4564


In image colorization, exemplar-based methods use a reference color image to guide the colorization of a target grayscale image. In this article, we present a deep learning framework for exemplar-based image colorization which relies on attention layers to capture robust correspondences between high-resolution deep features from pairs of images. To avoid the quadratic scaling problem from classic attention, we rely on a novel attention block computed from superpixel features, which we call super-attention. Super-attention blocks can learn to transfer semantically related color characteristics from a reference image at different scales of a deep network. Our experimental validations highlight the interest of this approach for exemplar-based colorization. We obtain promising results, achieving visually appealing colorization and outperforming state-of-the-art methods on different quantitative metrics.

Related Material

[pdf] [supp] [code]
@InProceedings{Carrillo_2022_ACCV, author = {Carrillo, Hernan and Cl\'ement, Micha\"el and Bugeau, Aurelie}, title = {Super-attention for exemplar-based image colorization}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {4548-4564} }