PhyEditBench: 一个用于物理感知图像编辑的真实世界多阶段基准
PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing
AI总结：
提出PhyEditBench基准，通过分层分类和真实/反物理实例评估编辑模型的物理理解能力，并引入训练无关基线PhyWorld利用视频生成推理。
摘要：
尽管基于指令的图像编辑在多模态生成模型的推动下取得了显著进展，但现有基准缺乏对基于物理的推理的全面评估，而这是处理真实世界场景的关键能力。为此，我们引入了PhyEditBench，一个旨在评估编辑模型物理理解能力的基准。在分层分类的指导下，我们建立了4个主类和12个子类。该基准包含238个从视频中精心提取的高质量、高分辨率真实世界实例，以捕捉真实的物理动态，以及35个合成的反物理实例。我们对当前最先进编辑方法的实证分析揭示了它们在基于物理的推理方面的重大局限性。我们进一步提出了一个名为PhyWorld的无训练基线，该基线使用测试时缩放和潜在缩减策略。PhyWorld优于同类模型，并表明视频生成过程可以有效地作为图像编辑的推理机制。项目页面可在此https URL获取。
英文摘要：
While instruction-based image editing, enabled by multi-modal generative models, has advanced significantly, existing benchmarks lack a comprehensive evaluation of physics-based reasoning, a critical capability for handling real-world scenarios. To address this, we introduce PhyEditBench, a benchmark designed to assess the physical understanding of editing models. Guided by a hierarchical taxonomy, we establish 4 primary classes and 12 subclasses. It comprises 238 high-quality, high-resolution, real-world instances meticulously extracted from videos to capture authentic physical dynamics, alongside 35 synthetic Anti-Physics instances. Our empirical analysis of current SOTA editing methods exposes substantial limitations in their physics-based reasoning. We further propose a training-free baseline named PhyWorld that uses test-time scaling and a latent reduction strategy. PhyWorld outperforms comparable models and suggests that the video generation process can effectively serve as a reasoning mechanism for image editing. The project page is available at https://github.com/Previsior/PhyEditBench.
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。
