Search papers, labs, and topics across Lattice.
This paper introduces NamedCurves+, a novel image enhancement method that leverages color naming to improve interpretability and user interaction in image retouching. By integrating a learning-based framework with tone curves for global color adjustments and a transformer block for local context-aware edits, NamedCurves+ allows users to intuitively modify images according to their preferences. Extensive experiments show that this approach not only enhances the retouching process but also outperforms existing state-of-the-art methods in tasks like tone mapping and exposure correction.
NamedCurves+ transforms image retouching by making color adjustments intuitive and customizable, outperforming traditional methods in both performance and user experience.
Enhancing images to make them visually appealing is a persistent challenge in computer vision. Many deep-learning methods train models on paired datasets to replicate expert editing styles. However, these approaches struggle with two key issues: (1) interpretability and (2) a parametrization suitable for user adjustments. To address these challenges, we present NamedCurves+, an approach inspired by the concept of Color Naming, a universal set of familiar colors widely used in software tools for intuitive editing. Our method integrates color names into a learning-based framework, enabling global adjustments for each named color through tone curves. To address local image variations, we incorporate a transformer block that captures spatial dependencies, enabling context-aware edits across the image. NamedCurves+ enhances the retouching process's interpretability and supports user interaction, allowing flexible modifications of individual tone curves to refine the retouched image according to personal preferences. Extensive experiments on tasks such as image retouching, tone mapping, and exposure correction demonstrate that NamedCurves+ outperforms state-of-the-art methods. Notably, our approach is both explainable, as the tone curves explicitly represent how each color name contributes to the enhancement, and interactive, allowing users to customize the retouching process and achieve results tailored to their liking. Source code and models will be publicly available at: https://namedcurves.github.io.
