将2D图像物体抬升至3D空间编辑，实现更一致的物体保持。
2D Instance Editing in 3D Space
- 通过3D空间约束编辑，避免2D像素操作导致的失真。
- 在多个数据集上显著提升编辑一致性与物体身份保留率。
- 适合需要精确控制物体形态的图像编辑场景。
生成模型在2D图像编辑方面取得显著进展，展现出极高的精度和真实感。然而，由于其固有的像素操作特性，常面临一致性与物体身份保持的问题。为解决这一局限，我们提出一种全新的“2D-3D-2D”框架。该方法首先将2D物体提升至3D表示，使其在符合物理规律、具有刚性约束的3D环境中进行编辑。编辑后的3D物体再被投影回原2D图像，并通过无缝修复方式融合。与现有2D编辑方法（如DragGAN、DragDiffusion）相比，我们的方法直接在3D空间中操作物体。大量实验表明，该框架在通用性能上超越先前方法，实现了高度一致的编辑效果，同时稳健地保留了物体身份。
原文摘要 · Abstract (English)
Generative models have achieved significant progress in advancing 2D image editing, demonstrating exceptional precision and realism. However, they often struggle with consistency and object identity preservation due to their inherent pixel-manipulation nature. To address this limitation, we introduce a novel "2D-3D-2D" framework. Our approach begins by lifting 2D objects into 3D representation, enabling edits within a physically plausible, rigidity-constrained 3D environment. The edited 3D objects are then reprojected and seamlessly inpainted back into the original 2D image. In contrast to existing 2D editing methods, such as DragGAN and DragDiffusion, our method directly manipulates objects in a 3D environment. Extensive experiments highlight that our framework surpasses previous methods in general performance, delivering highly consistent edits while robustly preserving object identity.
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。