IA-CLAHE: Image-Adaptive Clip Limit Estimation for CLAHE

2026-04-17

AI Summary

This work proposes an image-adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE) method that overcomes the limitations of conventional CLAHE, which employs a fixed clip limit and often suffers from over-enhancement due to varying local histogram characteristics. The proposed approach leverages a lightweight neural network to dynamically predict clip limits for each image tile, integrated within a differentiable CLAHE framework to enable end-to-end optimization. Notably, the method requires neither ground-truth clip limit annotations nor task-specific training data; instead, it achieves zero-shot generalization by mapping input histograms toward a domain-invariant uniform distribution. Experimental results demonstrate that the technique not only enhances visual perceptual quality but also significantly improves performance on downstream recognition tasks, all without reliance on task-related labeled data.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

This paper proposes image-adaptive contrast limited adaptive histogram equalization (IA-CLAHE). Conventional CLAHE is widely used to boost the performance of various computer vision tasks and to improve visual quality for human perception in practical industrial applications. CLAHE applies contrast limited histogram equalization to each local region to enhance local contrast. However, CLAHE often leads to over-enhancement, because the contrast-limiting parameter clip limit is fixed regardless of the histogram distribution of each local region. Our IA-CLAHE addresses this limitation by adaptively estimating tile-wise clip limits from the input image. To achieve this, we train a lightweight clip limits estimator with a differentiable extension of CLAHE, enabling end-to-end optimization. Unlike prior learning-based CLAHE methods, IA-CLAHE does not require pre-searched ground-truth clip limits or task-specific datasets, because it learns to map input image histograms toward a domain-invariant uniform distribution, enabling zero-shot generalization across diverse conditions. Experimental results show that IA-CLAHE consistently improves recognition performance, while simultaneously enhancing visual quality for human perception, without requiring any task-specific training data.

Problem

• CLAHE
• clip limit
• over-enhancement
• image enhancement
• adaptive histogram equalization

Innovation

• image-adaptive
• clip limit estimation
• differentiable CLAHE
• zero-shot generalization
• contrast enhancement