Venus: 多模态大语言模型在审美指导与裁剪中的基准测试与赋能
Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping
AI总结：
Venus通过两阶段框架提升多模态大语言模型的审美指导与裁剪能力，实现可解释的审美优化。
摘要：
智能手机的广泛使用使摄影变得普遍，但普通用户与专业摄影师之间仍存在明显差距，后者能够识别审美问题并在拍摄过程中提供可操作的拍摄指导。我们将这种能力定义为审美指导（AG）——在计算美学领域中是必不可少但长期被忽视的领域。现有的多模态大语言模型（MLLMs）主要提供过度积极的反馈，无法识别问题或提供可操作的指导。没有AG能力，它们无法有效识别分散区域或优化构图平衡，因此在审美裁剪中也面临挑战，审美裁剪旨在通过拍摄后重新构图来改进照片构图。为了解决这一问题，我们引入AesGuide，首个大规模AG数据集和基准，包含10,748张带有审美评分、分析和指导的图片。基于此，我们提出Venus，一个两阶段框架，首先通过逐步复杂的审美问题赋予MLLMs AG能力，然后通过基于CoT的推理激活其审美裁剪能力。大量实验表明，Venus显著提升了AG能力，并在审美裁剪中实现了最先进的（SOTA）性能，使在照片创作两个阶段中都能实现可解释和交互的审美优化。代码可在https://github.com/PKU-ICST-MIPL/Venus_CVPR2026获取。
英文摘要：
The widespread use of smartphones has made photography ubiquitous, yet a clear gap remains between ordinary users and professional photographers, who can identify aesthetic issues and provide actionable shooting guidance during capture. We define this capability as aesthetic guidance (AG) -- an essential but largely underexplored domain in computational aesthetics. Existing multimodal large language models (MLLMs) primarily offer overly positive feedback, failing to identify issues or provide actionable guidance. Without AG capability, they cannot effectively identify distracting regions or optimize compositional balance, thus also struggling in aesthetic cropping, which aims to refine photo composition through reframing after capture. To address this, we introduce AesGuide, the first large-scale AG dataset and benchmark with 10,748 photos annotated with aesthetic scores, analyses, and guidance. Building upon it, we propose Venus, a two-stage framework that first empowers MLLMs with AG capability through progressively complex aesthetic questions and then activates their aesthetic cropping power via CoT-based rationales. Extensive experiments show that Venus substantially improves AG capability and achieves state-of-the-art (SOTA) performance in aesthetic cropping, enabling interpretable and interactive aesthetic refinement across both stages of photo creation. Code is available at https://github.com/PKU-ICST-MIPL/Venus_CVPR2026.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
