基于分层场景扩散的任意物体移动
Move Anything with Layered Scene Diffusion
AI总结：
针对扩散模型难以自由调整图像布局的问题，提出无需训练的SceneDiffusion方法，通过扩散采样中优化分层场景表示、联合去噪不同布局渲染实现空间解耦，支持多种空间与分层编辑，还可处理真实图像，响应不到1秒。
摘要：
扩散模型生成图像的质量达到了前所未有的水平，但我们如何才能自由 rearrange 图像布局？近期研究通过学习空间解耦的潜在码生成可控场景，但这类方法因扩散模型的前向过程固定而无法适用。本文提出 SceneDiffusion，在扩散采样过程中优化分层场景表示。核心思路是通过联合对不同空间布局下的场景渲染结果去噪，实现空间解耦。我们生成的场景支持多种空间编辑操作，包括移动、调整大小、克隆，以及分层外观编辑操作，如物体风格重设与替换。此外，还能以参考图像为条件生成场景，从而实现真实图像（in-the-wild images）中的物体移动。值得注意的是，该方法无需训练，兼容通用文本到图像扩散模型，且响应时间不到1秒。
英文摘要：
Diffusion models generate images with an unprecedented level of quality, but how can we freely rearrange image layouts? Recent works generate controllable scenes via learning spatially disentangled latent codes, but these methods do not apply to diffusion models due to their fixed forward process. In this work, we propose SceneDiffusion to optimize a layered scene representation during the diffusion sampling process. Our key insight is that spatial disentanglement can be obtained by jointly denoising scene renderings at different spatial layouts. Our generated scenes support a wide range of spatial editing operations, including moving, resizing, cloning, and layer-wise appearance editing operations, including object restyling and replacing. Moreover, a scene can be generated conditioned on a reference image, thus enabling object moving for in-the-wild images. Notably, this approach is training-free, compatible with general text-to-image diffusion models, and responsive in less than a second.
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。
