DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal

2025-11-15

AI Summary

Purple fringing (PF), caused by longitudinal chromatic aberration (LCA) in camera lenses, severely degrades image sharpness and color fidelity. To address this physically grounded problem, we propose the first deep learning-based PF removal method explicitly modeling its optical origin: a color-aware coordinate transformation module explicitly captures spatial misalignment across RGB channels; an image-adaptive color space modeling scheme coupled with a 5D lookup table (LUT) enables efficient nonlinear color correction. Our approach embeds optical priors directly into the network architecture, eliminating reliance on hand-crafted features or expensive apochromatic (APO) lenses. Extensive experiments on both synthetic and real-world datasets demonstrate state-of-the-art performance—effectively suppressing PF while restoring natural, sharp visual quality.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional solutions rely on complex and expensive apochromatic (APO) lens hardware and the extraction of handcrafted features, ignoring the data-driven approach. To fill this gap, we introduce DCA-LUT, the first deep learning framework for purple fringing removal. Inspired by the physical root of the problem, the spatial misalignment of RGB color channels due to lens dispersion, we introduce a novel Chromatic-Aware Coordinate Transformation (CA-CT) module, learning an image-adaptive color space to decouple and isolate fringing into a dedicated dimension. This targeted separation allows the network to learn a precise ``purple fringe channel", which then guides the accurate restoration of the luminance channel. The final color correction is performed by a learned 5D Look-Up Table (5D LUT), enabling efficient and powerful% non-linear color mapping. To enable robust training and fair evaluation, we constructed a large-scale synthetic purple fringing dataset (PF-Synth). Extensive experiments in synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in purple fringing removal.

Problem

• Removing purple fringing artifacts from digital images
• Addressing color channel misalignment caused by lens dispersion
• Providing data-driven alternative to hardware-dependent correction methods

Innovation

• Deep learning framework for purple fringing removal
• Chromatic-Aware Coordinate Transformation module for fringing isolation
• Learned 5D Look-Up Table for efficient color correction