首个针对室内空间美学的评估框架，可量化布局、和谐、光照等维度。
Beyond Pixels: Benchmarking and Reward-Based Assessing Framework for Visual Spatial Aesthetics
- 构建四维美学评估体系，涵盖布局、和谐、光照与失真。
- 创建包含1.8万张图像和5万条标注的SA-BENCH基准数据集。
- 可用于优化AI绘图生成质量，适合图像生成与评价研究者。
近年来，人工智能生成图像（AIGI）的图像质量评估（IQA）发展迅速；然而现有方法主要聚焦于人像与艺术图像，缺乏对室内场景的系统性评估。我们提出空间美学（Spatial Aesthetics）新范式，从布局、和谐、光照和失真四个维度评估室内图像的美学质量。构建了首个空间美学基准SA-BENCH，包含18,000张图像和50,000条精确标注。基于该基准，我们系统评估现有IQA方法，并通过多模态大模型（MLLM）微调与多维度融合，提出SA-IQA，作为全面的空间美学奖励框架。将其应用于两个下游任务：（1）作为奖励信号集成至GRPO强化学习中，优化AIGC生成流程；（2）用于Best-of-N筛选，提升生成图像质量。实验表明，SA-IQA在SA-BENCH上显著优于现有方法，树立了空间美学评估的新标准。代码已开源：https://github.com/AlibabaResearch/SA-IQA。
原文摘要 · Abstract (English)
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 is available at https://github.com/AlibabaResearch/SA-IQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。