UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark

TL;DR

This paper introduces UNIAA, a unified multi-modal framework for image aesthetic assessment using large language models, along with a comprehensive benchmark to evaluate multi-level aesthetic understanding, demonstrating promising results and potential for future improvements.

Contribution

The work presents a novel unified multi-modal approach for image aesthetic assessment and establishes a comprehensive benchmark to evaluate multi-level aesthetic understanding.

Findings

UNIAA-LLaVA outperforms existing MLLMs in aesthetic perception.

UNIAA-LLaVA approaches junior-level human performance.

The benchmark covers perception, description, and assessment levels.

Abstract

As an alternative to expensive expert evaluation, Image Aesthetic Assessment (IAA) stands out as a crucial task in computer vision. However, traditional IAA methods are typically constrained to a single data source or task, restricting the universality and broader application. In this work, to better align with human aesthetics, we propose a Unified Multi-modal Image Aesthetic Assessment (UNIAA) framework, including a Multi-modal Large Language Model (MLLM) named UNIAA-LLaVA and a comprehensive benchmark named UNIAA-Bench. We choose MLLMs with both visual perception and language ability for IAA and establish a low-cost paradigm for transforming the existing datasets into unified and high-quality visual instruction tuning data, from which the UNIAA-LLaVA is trained. To further evaluate the IAA capability of MLLMs, we construct the UNIAA-Bench, which consists of three aesthetic levels: Perception, Description, and Assessment. Extensive experiments validate the effectiveness and rationality of UNIAA. UNIAA-LLaVA achieves competitive performance on all levels of UNIAA-Bench, compared with existing MLLMs. Specifically, our model performs better than GPT-4V in aesthetic perception and even approaches the junior-level human. We find MLLMs have great potential in IAA, yet there remains plenty of room for further improvement. The UNIAA-LLaVA and UNIAA-Bench will be released.