Content-Adaptive Image Retouching Guided by Attribute-Based Text Representation

2025-12-10

AI Summary

Existing image retouching methods rely on global pixel-wise color mapping, neglecting semantic content variations and user-specific style preferences—leading to color distortion, regional inconsistency, and inadequate style alignment. To address these limitations, we propose a content-adaptive curve mapping framework integrated with attribute-driven textual representation learning. Our approach introduces a novel multi-basis curve mapping mechanism that enables semantic-region-aware, context-sensitive color adjustment. We further design an attribute text prediction module to generate interpretable, fine-grained style descriptions, and construct a vision-language cross-modal fusion architecture coupled with a learnable weight map estimation module for adaptive spatial modulation. Evaluated on multiple public benchmarks, our method achieves state-of-the-art performance, significantly improving color fidelity, regional consistency, and alignment with user-defined stylistic preferences.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

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
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Image retouching has received significant attention due to its ability to achieve high-quality visual content. Existing approaches mainly rely on uniform pixel-wise color mapping across entire images, neglecting the inherent color variations induced by image content. This limitation hinders existing approaches from achieving adaptive retouching that accommodates both diverse color distributions and user-defined style preferences. To address these challenges, we propose a novel Content-Adaptive image retouching method guided by Attribute-based Text Representation (CA-ATP). Specifically, we propose a content-adaptive curve mapping module, which leverages a series of basis curves to establish multiple color mapping relationships and learns the corresponding weight maps, enabling content-aware color adjustments. The proposed module can capture color diversity within the image content, allowing similar color values to receive distinct transformations based on their spatial context. In addition, we propose an attribute text prediction module that generates text representations from multiple image attributes, which explicitly represent user-defined style preferences. These attribute-based text representations are subsequently integrated with visual features via a multimodal model, providing user-friendly guidance for image retouching. Extensive experiments on several public datasets demonstrate that our method achieves state-of-the-art performance.

Problem

• Adaptive image retouching for diverse color distributions
• Integrating user-defined style preferences via text guidance
• Overcoming uniform color mapping limitations with content-aware adjustments

Innovation

• Content-adaptive curve mapping for color adjustments
• Attribute-based text representation for style guidance
• Multimodal integration of text and visual features