CAST-LUT: Tokenizer-Guided HSV Look-Up Tables for Purple Flare Removal

2025-11-10

AI Summary

Purple flare—a chromatic aberration artifact prevalent in overexposed regions—severely degrades tonal transitions and color fidelity. Addressing the challenges of scarce paired training data and inflexible, fixed-prior assumptions in existing methods, this paper proposes a two-stage end-to-end restoration framework based on a decoupled HSV lookup table (LUT). Key contributions include: (1) the first chroma-aware spectral tokenizer coupled with a dynamic 1D-LUT generation mechanism; (2) the construction of the first large-scale synthetic purple-flare dataset; and (3) an HSV-space decoupled correction strategy, alongside dedicated evaluation metrics and loss functions. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both visual quality and quantitative metrics—including PSNR, SSIM, and LPIPS—significantly outperforming prior approaches.

Technology Category

• Computer Vision: Segmentation
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Privacy-enhancing technologies

Abstract

Purple flare, a diffuse chromatic aberration artifact commonly found around highlight areas, severely degrades the tone transition and color of the image. Existing traditional methods are based on hand-crafted features, which lack flexibility and rely entirely on fixed priors, while the scarcity of paired training data critically hampers deep learning. To address this issue, we propose a novel network built upon decoupled HSV Look-Up Tables (LUTs). The method aims to simplify color correction by adjusting the Hue (H), Saturation (S), and Value (V) components independently. This approach resolves the inherent color coupling problems in traditional methods. Our model adopts a two-stage architecture: First, a Chroma-Aware Spectral Tokenizer (CAST) converts the input image from RGB space to HSV space and independently encodes the Hue (H) and Value (V) channels into a set of semantic tokens describing the Purple flare status; second, the HSV-LUT module takes these tokens as input and dynamically generates independent correction curves (1D-LUTs) for the three channels H, S, and V. To effectively train and validate our model, we built the first large-scale purple flare dataset with diverse scenes. We also proposed new metrics and a loss function specifically designed for this task. Extensive experiments demonstrate that our model not only significantly outperforms existing methods in visual effects but also achieves state-of-the-art performance on all quantitative metrics.

Problem

• Removing purple flare artifacts from images
• Addressing color coupling in HSV correction methods
• Overcoming scarcity of paired training data

Innovation

• Tokenizer-guided HSV LUTs for flare removal
• Two-stage architecture with semantic token encoding
• Independent H S V channel correction curves