Edit360: 2D Image Edits to 3D Assets From Any Angle

作者：Junchao Huang, Xinting Hu, Shaoshuai Shi, Zhuotao Tian, Li Jiang · 发表于：IEEE International Conference on Computer Vision · 年份：2025 · DOI：10.1109/ICCV51701.2025.01543 · 被引用次数：11 · 研究领域：Computer Science

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 view-points while ensuring structural coherence across all views. The framework selects anchor views for $2 D$ 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 multiview sequences facilitate the reconstruction of high-quality 3D assets, enabling customizable 3D content creation.