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

TL;DR

This paper introduces a content-adaptive image retouching method guided by attribute-based text representations, enabling personalized and context-aware color adjustments that outperform existing uniform approaches.

Contribution

The paper presents a novel content-adaptive retouching framework that integrates attribute-based text guidance with a multi-curve mapping module for improved visual quality.

Findings

Achieves state-of-the-art retouching performance on public datasets.

Effectively captures color diversity and user preferences.

Outperforms existing uniform retouching methods.

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.