SpatialEdit：细粒度图像空间编辑基准测试
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
AI总结：
本文提出SpatialEdit-Bench基准测试，结合视角重建和框架分析评估空间编辑的感知合理性和几何精度，并构建了SpatialEdit-500k合成数据集和SpatialEdit-16B基线模型，实现细粒度空间编辑的高效训练与评估。
摘要：
图像空间编辑通过几何驱动的变换，实现对物体布局和摄像机视角的精确控制。当前模型在细粒度空间操作上表现不足，因此需要专门的评估套件。本文的贡献包括：(i) 提出SpatialEdit-Bench基准测试，通过视角重建和框架分析联合测量感知合理性与几何精度；(ii) 为解决可扩展训练的数据瓶颈，构建了使用可控Blender管道生成的SpatialEdit-500k合成数据集，提供精确的地面真实变换；(iii) 基于此数据集开发了SpatialEdit-16B基线模型，在一般编辑任务中表现优异，在空间操作任务中显著优于现有方法。所有资源将在https://github.com/EasonXiao-888/SpatialEdit公开。
英文摘要：
Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints. Current models are insufficient for fine-grained spatial manipulations, motivating a dedicated assessment suite. Our contributions are listed: (i) We introduce SpatialEdit-Bench, a complete benchmark that evaluates spatial editing by jointly measuring perceptual plausibility and geometric fidelity via viewpoint reconstruction and framing analysis. (ii) To address the data bottleneck for scalable training, we construct SpatialEdit-500k, a synthetic dataset generated with a controllable Blender pipeline that renders objects across diverse backgrounds and systematic camera trajectories, providing precise ground-truth transformations for both object- and camera-centric operations. (iii) Building on this data, we develop SpatialEdit-16B, a baseline model for fine-grained spatial editing. Our method achieves competitive performance on general editing while substantially outperforming prior methods on spatial manipulation tasks. All resources will be made public at https://github.com/EasonXiao-888/SpatialEdit.
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。
