无需微调，任意视角下实现2D图像编辑到3D资产的多视角一致转换。
Edit360: 2D Image Edits to 3D Assets from Any Angle
- 基于视频扩散模型，通过锚点视图传播编辑至360度全视角。
- 支持用户自定义视角的精细编辑，保持所有视角结构一致。
- 适合需要灵活生成3D内容的创作者和设计师使用。
近期扩散模型在图像生成与编辑方面取得显著进展，但将其能力扩展至3D资产仍具挑战性，尤其在需多视角一致性的细粒度编辑方面。现有方法通常受限于预设视角，严重限制灵活性与实用性。我们提出Edit360，一个无需微调的框架，可将2D修改扩展至多视角一致的3D编辑。该框架基于视频扩散模型，支持从任意视角进行用户定制化编辑，同时确保所有视角间结构一致性。其核心是引入新颖的锚点视图编辑传播机制，在扩散模型的潜在空间与注意力空间内有效对齐并融合多视角信息。由此生成的多视角序列可重建高质量3D资产，实现可定制的3D内容创作。
原文摘要 · Abstract (English)
Recent advances in diffusion models have significantly improved image generation and editing, but extending these capabilities to 3D assets remains challenging, especially for fine-grained edits that require multi-view consistency. Existing methods typically restrict editing to predetermined viewing angles, severely limiting their flexibility and practical applications. We introduce Edit360, a tuning-free framework that extends 2D modifications to multi-view consistent 3D editing. Built upon video diffusion models, Edit360 enables user-specific editing from arbitrary viewpoints while ensuring structural coherence across all views. The framework selects anchor views for 2D modifications and propagates edits across the entire 360-degree range. To achieve this, Edit360 introduces a novel Anchor-View Editing Propagation mechanism, which effectively aligns and merges multi-view information within the latent and attention spaces of diffusion models. The resulting edited multi-view sequences facilitate the reconstruction of high-quality 3D assets, enabling customizable 3D content creation.
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。