Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization

TL;DR

This paper introduces a novel exemplar-based image colorization method leveraging the self-attention capabilities of pre-trained diffusion models, achieving improved semantic matching and color fidelity without additional training.

Contribution

It proposes a fine-tuning-free approach using dual attention-guided color transfer and classifier-free guidance, enhancing colorization quality and semantic alignment in reference-based image colorization.

Findings

Outperforms existing methods in image quality and fidelity.

Achieves an FID of 95.27 and SI-FID of 5.51 on benchmark pairs.

Utilizes dual attention for precise semantic correspondence.

Abstract

Exemplar-based image colorization aims to colorize a grayscale image using a reference color image, ensuring that reference colors are applied to corresponding input regions based on their semantic similarity. To achieve accurate semantic matching between regions, we leverage the self-attention module of a pre-trained diffusion model, which is trained on a large dataset and exhibits powerful attention capabilities. To harness this power, we propose a novel, fine-tuning-free approach based on a pre-trained diffusion model, making two key contributions. First, we introduce dual attention-guided color transfer. We utilize the self-attention module to compute an attention map between the input and reference images, effectively capturing semantic correspondences. The color features from the reference image is then transferred to the semantically matching regions of the input image, guided by this attention map, and finally, the grayscale features are replaced with the corresponding color features. Notably, we utilize dual attention to calculate attention maps separately for the grayscale and color images, achieving more precise semantic alignment. Second, we propose classifier-free colorization guidance, which enhances the transferred colors by combining color-transferred and non-color-transferred outputs. This process improves the quality of colorization. Our experimental results demonstrate that our method outperforms existing techniques in terms of image quality and fidelity to the reference. Specifically, we use 335 input-reference pairs from previous research, achieving an FID of 95.27 (image quality) and an SI-FID of 5.51 (fidelity to the reference). Our source code is available at https://github.com/satoshi-kosugi/powerful-attention.