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

• URL: http://arxiv.org/abs/2505.15812v1
• Date: Wed, 21 May 2025 17:59:40 GMT
• Title: Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization
• Authors: Satoshi Kosugi,
• Abstract summary: Exemplar-based image colorization aims to colorize a grayscale image using a reference color image.<n>We propose a novel, fine-tuning-free approach based on a pre-trained diffusion model.<n>Our experimental results demonstrate that our method outperforms existing techniques in terms of image quality and fidelity to the reference.
• Score: 4.233370898095789
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models [53.73253164099701]
  We introduce ColorWave, a training-free approach that achieves exact RGB-level color control in diffusion models without fine-tuning.<n>We demonstrate that ColorWave establishes a new paradigm for structured, color-consistent diffusion-based image synthesis.
  arXiv  Detail & Related papers  (2025-03-12T21:49:52Z)
• MangaNinja: Line Art Colorization with Precise Reference Following [84.2001766692797]
  MangaNinjia specializes in the task of reference-guided line art colorization.<n>We incorporate two thoughtful designs to ensure precise character detail transcription.<n>A patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching.
  arXiv  Detail & Related papers  (2025-01-14T18:59:55Z)
• ColorFlow: Retrieval-Augmented Image Sequence Colorization [65.93834649502898]
  We propose a three-stage diffusion-based framework tailored for image sequence colorization in industrial applications.<n>Unlike existing methods that require per-ID finetuning or explicit ID embedding extraction, we propose a novel Retrieval Augmented Colorization pipeline.<n>Our pipeline also features a dual-branch design: one branch for color identity extraction and the other for colorization.
  arXiv  Detail & Related papers  (2024-12-16T14:32:49Z)
• Paint Bucket Colorization Using Anime Character Color Design Sheets [72.66788521378864]
  We introduce inclusion matching, which allows the network to understand the relationships between segments. Our network's training pipeline significantly improves performance in both colorization and consecutive frame colorization. To support our network's training, we have developed a unique dataset named PaintBucket-Character.
  arXiv  Detail & Related papers  (2024-10-25T09:33:27Z)
• Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis [16.634138745034733]
  We present the first training-free, test-time-only method to disentangle and condition text-to-image models on color and style attributes from reference image.
  arXiv  Detail & Related papers  (2024-09-04T04:16:58Z)
• MultiColor: Image Colorization by Learning from Multiple Color Spaces [4.738828630428634]
  MultiColor is a new learning-based approach to automatically colorize grayscale images. We employ a set of dedicated colorization modules for individual color space. With these predicted color channels representing various color spaces, a complementary network is designed to exploit the complementarity and generate pleasing and reasonable colorized images.
  arXiv  Detail & Related papers  (2024-08-08T02:34:41Z)
• Improved Diffusion-based Image Colorization via Piggybacked Models [19.807766482434563]
  We introduce a colorization model piggybacking on the existing powerful T2I diffusion model. A diffusion guider is designed to incorporate the pre-trained weights of the latent diffusion model. A lightness-aware VQVAE will then generate the colorized result with pixel-perfect alignment to the given grayscale image.
  arXiv  Detail & Related papers  (2023-04-21T16:23:24Z)
• Detecting Recolored Image by Spatial Correlation [60.08643417333974]
  Image recoloring is an emerging editing technique that can manipulate the color values of an image to give it a new style. In this paper, we explore a solution from the perspective of the spatial correlation, which exhibits the generic detection capability for both conventional and deep learning-based recoloring. Our method achieves the state-of-the-art detection accuracy on multiple benchmark datasets and exhibits well generalization for unknown types of recoloring methods.
  arXiv  Detail & Related papers  (2022-04-23T01:54:06Z)
• Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization [23.301799487207035]
  Exemplar-based colorization approaches rely on reference image to provide plausible colors for target gray-scale image. We propose Semantic-Sparse Colorization Network (SSCN) to transfer both the global image style and semantic-related colors to the gray-scale image. Our network can perfectly balance the global and local colors while alleviating the ambiguous matching problem.
  arXiv  Detail & Related papers  (2021-12-02T15:35:10Z)
• Color2Style: Real-Time Exemplar-Based Image Colorization with Self-Reference Learning and Deep Feature Modulation [29.270149925368674]
  We present a deep exemplar-based image colorization approach named Color2Style to resurrect grayscale image media by filling them with vibrant colors. Our method exploits a simple yet effective deep feature modulation (DFM) module, which injects the color embeddings extracted from the reference image into the deep representations of the input grayscale image.
  arXiv  Detail & Related papers  (2021-06-15T10:05:58Z)
• Instance-aware Image Colorization [51.12040118366072]
  In this paper, we propose a method for achieving instance-aware colorization. Our network architecture leverages an off-the-shelf object detector to obtain cropped object images. We use a similar network to extract the full-image features and apply a fusion module to predict the final colors.
  arXiv  Detail & Related papers  (2020-05-21T17:59:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.