SA-IQA: Redefining Image Quality Assessment for Spatial Aesthetics with Multi-Dimensional Rewards

TL;DR

This paper introduces SA-IQA, a novel image quality assessment framework focused on spatial aesthetics of interior images, utilizing a new benchmark and multi-dimensional rewards to improve AI-generated image evaluation and selection.

Contribution

The paper presents SA-IQA, the first comprehensive spatial aesthetics assessment method for interior images, along with SA-BENCH, a large annotated benchmark dataset, and demonstrates its effectiveness in AI image generation tasks.

Findings

SA-IQA outperforms existing IQA methods on SA-BENCH.

SA-IQA improves AI-generated image quality through reinforcement learning.

The benchmark contains 18,000 images with 50,000 annotations.

Abstract

In recent years, Image Quality Assessment (IQA) for AI-generated images (AIGI) has advanced rapidly; however, existing methods primarily target portraits and artistic images, lacking a systematic evaluation of interior scenes. We introduce Spatial Aesthetics, a paradigm that assesses the aesthetic quality of interior images along four dimensions: layout, harmony, lighting, and distortion. We construct SA-BENCH, the first benchmark for spatial aesthetics, comprising 18,000 images and 50,000 precise annotations. Employing SA-BENCH, we systematically evaluate current IQA methodologies and develop SA-IQA, through MLLM fine-tuning and a multidimensional fusion approach, as a comprehensive reward framework for assessing spatial aesthetics. We apply SA-IQA to two downstream tasks: (1) serving as a reward signal integrated with GRPO reinforcement learning to optimize the AIGC generation pipeline, and (2) Best-of-N selection to filter high-quality images and improve generation quality. Experiments indicate that SA-IQA significantly outperforms existing methods on SA-BENCH, setting a new standard for spatial aesthetics evaluation. Code and dataset will be open-sourced to advance research and applications in this domain.