用两张图实现无遮罩3D编辑，让修改自然跨视角保持一致。
EditP23: 3D Editing via Propagation of Image Prompts to Multi-View
- 通过原始图和编辑后图像引导隐空间流，实现3D一致性传播
- 无需手动掩码或文本提示，可保持物体结构与外观不变
- 适用于多种物体类别，适合快速直观的3D内容编辑
我们提出EditP23，一种无需掩码的3D编辑方法，通过在多视角表示中以3D一致的方式传播2D图像编辑。与依赖文本提示或显式空间掩码的传统方法不同，EditP23通过一对图像——原始视图及其用户编辑后的版本——进行条件控制。这些图像提示用于引导预训练多视角扩散模型隐空间中的编辑感知流，使编辑能够一致地传播至各视角。该方法为前向传播，无需优化，同时保持原物体的身份（结构与外观）。我们在多种物体类别和编辑场景中验证了其有效性，实现了对源图像的高度保真度，且无需手动掩码。
原文摘要 · Abstract (English)
We present EditP23, a method for mask-free 3D editing that propagates 2D image edits to multi-view representations in a 3D-consistent manner. In contrast to traditional approaches that rely on text-based prompting or explicit spatial masks, EditP23 enables intuitive edits by conditioning on a pair of images: an original view and its user-edited counterpart. These image prompts are used to guide an edit-aware flow in the latent space of a pre-trained multi-view diffusion model, allowing the edit to be coherently propagated across views. Our method operates in a feed-forward manner, without optimization, and preserves the identity of the original object, in both structure and appearance. We demonstrate its effectiveness across a range of object categories and editing scenarios, achieving high fidelity to the source while requiring no manual masks.
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。