Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion

• URL: http://arxiv.org/abs/2603.18466v1
• Date: Thu, 19 Mar 2026 03:53:38 GMT
• Title: Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusion
• Abstract summary: Colour is one of the most perceptually salient yet least controllable attributes in image generation.<n>ColourCrafter transforms colour editing from global tone transfer into a structured, region-aware generation process.<n>We build ColourfulSet, a largescale dataset of high-quality image pairs with continuous and diverse colour variations.
• Score: 43.72039047537043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructions, their results often deviate from the intended hue, especially for fine-grained and local edits. Early text-driven methods rely on discrete language descriptions that cannot accurately represent continuous chromatic variations. To overcome this limitation, we propose ColourCrafter, a unified diffusion framework that transforms colour editing from global tone transfer into a structured, region-aware generation process. Unlike traditional colour driven methods, ColourCrafter performs token-level fusion of RGB colour tokens and image tokens in latent space, selectively propagating colour information to semantically relevant regions while preserving structural fidelity. A perceptual Lab-space Loss further enhances pixel-level precision by decoupling luminance and chrominance and constraining edits within masked areas. Additionally, we build ColourfulSet, a largescale dataset of high-quality image pairs with continuous and diverse colour variations. Extensive experiments demonstrate that ColourCrafter achieves state-of-the-art colour accuracy, controllability and perceptual fidelity in fine-grained colour editing. Our project is available at https://yangyuqi317.github.io/ColourCrafter.github.io/.

Related papers

• NumColor: Precise Numeric Color Control in Text-to-Image Generation [57.72106507860579]
  Text-to-image models excel at generating images from natural language descriptions, yet fail to interpret numerical colors.<n>We present NumColor, that enables precise numerical color control across multiple diffusion architectures.<n> NumColor improves numerical color accuracy by 4-9x across five models, while simultaneously improving color harmony scores by 10-30x on GenColorBench benchmark.
  arXiv  Detail & Related papers  (2026-03-13T19:37:25Z)
• Controllable-Continuous Color Editing in Diffusion Model via Color Mapping [73.62340517056619]
  We introduce a color mapping module that explicitly models the correspondence between the text embedding space and image RGB values.<n>Users can specify a target RGB range to generate images with continuous color variations within the desired range.<n> Experimental results demonstrate that our method performs well in terms of color continuity and controllability.
  arXiv  Detail & Related papers  (2025-09-17T07:12:51Z)
• Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation [21.37070510103594]
  Existing approaches rely on cross-attention manipulation, reference images, or fine-tuning to resolve ambiguous color descriptions.<n>We propose a training-free framework that enhances color fidelity by leveraging a large language model (LLM) to disambiguate color-related prompts.<n>Our method first employs a large language model (LLM) to resolve ambiguous color terms in the text prompt, and then refines the text embeddings based on the spatial relationships of the resulting color terms.
  arXiv  Detail & Related papers  (2025-09-12T08:44:22Z)
• Semantic Palette-Guided Color Propagation [7.263538036771765]
  Conventional approaches often rely on low-level visual cues such as color, texture, or lightness to measure pixel similarity.<n>We present a semantic palette-guided approach for color propagation.<n>Our approach enables efficient yet accurate pixel-level color editing and ensures that local color changes are propagated in a content-aware manner.
  arXiv  Detail & Related papers  (2025-06-02T08:57:34Z)
• Free-Lunch Color-Texture Disentanglement for Stylized Image Generation [62.215875006311876]
  This paper introduces the first tuning-free approach to achieve free-lunch color-texture disentanglement in stylized T2I generation.<n>Our Style Attributes Disentanglement approach (SADis) delivers a more precise and customizable solution for stylized image generation.<n> Experiments on images from the WikiArt and StyleDrop datasets demonstrate that, both qualitatively and quantitatively, SADis surpasses state-of-the-artization methods in the DisIG task.
  arXiv  Detail & Related papers  (2025-03-18T14:10:43Z)
• Control Color: Multimodal Diffusion-based Interactive Image Colorization [81.68817300796644]
  Control Color (Ctrl Color) is a multi-modal colorization method that leverages the pre-trained Stable Diffusion (SD) model. We present an effective way to encode user strokes to enable precise local color manipulation. We also introduce a novel module based on self-attention and a content-guided deformable autoencoder to address the long-standing issues of color overflow and inaccurate coloring.
  arXiv  Detail & Related papers  (2024-02-16T17:51:13Z)
• DiffColor: Toward High Fidelity Text-Guided Image Colorization with Diffusion Models [12.897939032560537]
  We propose a new method called DiffColor to recover vivid colors conditioned on a prompt text. We first fine-tune a pre-trained text-to-image model to generate colorized images using a CLIP-based contrastive loss. Then we try to obtain an optimized text embedding aligning the colorized image and the text prompt, and a fine-tuned diffusion model enabling high-quality image reconstruction. Our method can produce vivid and diverse colors with a few iterations, and keep the structure and background intact while having colors well-aligned with the target language guidance.
  arXiv  Detail & Related papers  (2023-08-03T09:38:35Z)
• Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer [62.75343115345667]
  We propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining machine recognition on the quantised images. We observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage.
  arXiv  Detail & Related papers  (2022-12-07T03:39:18Z)

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.