SinColor: Uncertainty-Guided Single-Step Diffusion for Image Colorization
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1
Abstract
Image colorization is a fundamental yet challenging task in computer vision, aiming to recover plausible and spatially coherent colors from grayscale images. Recent advancements in diffusion models have enabled significant progress in this field, yet existing methods predominantly rely on multi-step diffusion processes. While effective for generating high-frequency details, these approaches are suboptimal for colorization, as color information is inherently low-frequency, spatially smooth, and globally consistent. This mismatch leads to two critical limitations: (1) color artifacts and inconsistency due to excessive noise in the color space, and (2) high computational cost that hinders practical application. In this work, we propose a novel single-step diffusion framework for efficient and high-quality image colorization. We introduce a color uncertainty estimation (CUE) module to identify reliable and uncertain regions in the image, allowing the model to prioritize local certainty while reasoning about confused regions. To focus the model on low-frequency color generation, we directly encode the grayscale image into a latent representation, remove structural components in the output, and reconstruct the final image via efficient decoding. Extensive experiments on ImageNet, COCO-Stuff, and Extended COCO-Stuff demonstrate that our approach achieves state-of-the-art performance while reducing inference time by 98% and trainable parameters by 97% compared to leading multi-step diffusion methods. Our contributions include a systematic analysis of diffusion-based colorization, a lightweight yet effective uncertainty-aware framework, and comprehensive validation of its efficiency and effectiveness.Keywords
Funding Information
- Major Projects of National Natural Science Foundation of China (72293580/72293583)
- Agency for Science, Technology and Research (A*STAR) under its AME Programmatic Funds (A20H6b0151)
- Hainan Provincial Joint Project of Li'an International Education Innovation pilot Zone (624LALH002)
- Foundation of Key Laboratory of Big Data and Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education (BATLAB202403)
This publication has 27 references indexed in Scilit:
- Adversarial Diffusion Distillation2024
- SinSR: Diffusion-Based Image Super-Resolution in a Single Step2024
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Instance-Aware Image Colorization2020
- COCO-Stuff: Thing and Stuff Classes in Context2018
- Unsupervised Diverse Colorization via Generative Adversarial Networks2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Colorful Image Colorization2016
- Learning Representations for Automatic Colorization2016
- ImageNet: A large-scale hierarchical image database2009