TY - GEN
T1 - Edit360
T2 - 2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025
AU - Huang, Junchao
AU - Hu, Xinting
AU - Shi, Shaoshuai
AU - Tian, Zhuotao
AU - Jiang, Li
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - 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 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 multiview sequences facilitate the reconstruction of high-quality 3D assets, enabling customizable 3D content creation.
AB - 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 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 multiview sequences facilitate the reconstruction of high-quality 3D assets, enabling customizable 3D content creation.
KW - 3d asset generation
KW - customizable 3d editing
KW - video diffusion models
UR - https://www.scopus.com/pages/publications/105044221181
U2 - 10.1109/ICCV51701.2025.01543
DO - 10.1109/ICCV51701.2025.01543
M3 - 会议稿件
AN - SCOPUS:105044221181
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 16618
EP - 16628
BT - Proceedings - 2025 IEEE/CVF International Conference on Computer Vision, ICCV 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 October 2025 through 23 October 2025
ER -