ReART: Reference-Guided Retrieval and Refinement for Emotion-Aware Art Generation

2026-08-23

AI Summary

为解决情感感知艺术图像生成中的细粒度视觉属性难以具体化的问题，提出ReART框架，通过结构化视觉字段分解与检索及AAS驱动的细化循环来实现。

Abstract

Emotion-aware artistic image generation requires a model to satisfy semantic content, artistic style, and target emotion simultaneously. The key challenge is that artistic captions conflate these axes into underspecified free-form text, making fine-grained visual attributes such as brushwork, composition, and tonal atmosphere difficult to ground concretely. We present ReART, a reference-guided retrieval and refinement framework. Our method decomposes test captions and each image annotation in the EmoArt database into structured visual fields, and performs field-wise retrieval over subject, layout, brush-line, and tone-mood dimensions to retrieve role-specific visual references that supply the perceptual detail text alone cannot convey; these references are used alongside a structured prompt for initial synthesis. For samples where any Attribute Alignment Score (AAS) axis falls below threshold, an AAS-driven refinement loop diagnoses failures, constructs constrained repair plans specifying elements to keep, errors to fix, and operations to avoid, routes references by correction purpose, and performs controlled editing under structural preservation constraints. Our system ranks 2nd in Track 1 of the AffectiveArt 2026 Grand Challenge, achieving a perfect AAS of 1.00 and an overall score of 0.78. Code is available at https://github.com/oceanflowlab/ReART.git.

Problem

• emotion-aware
• artistic image generation
• semantic content
• artistic style
• target emotion

Innovation

• Reference-Guided Retrieval
• Attribute Alignment Score (AAS)
• Controlled Editing
• Emotion-Aware Art Generation