3D-Consistent Multi-View Editing by Correspondence Guidance
Quick summary
arXiv:2511.22228v3 Announce Type: replace-cross Abstract: Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently often produce geometrically and photometrically inconsistent results across different views of the same scene. Such inconsistencies are particularly problematic for editing of 3D representations such as NeRFs or Gaussian splat models. We propose a training-free guidance framework that enforces multi-view consistency during the image editing process. The key idea is that corresponding points should l
Key takeaways
- arXiv:2511.22228v3 Announce Type: replace-cross Abstract: Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently often produce geometrically and photometrically inconsistent results across different views of the same scene.
- Such inconsistencies are particularly problematic for editing of 3D representations such as NeRFs or Gaussian splat models.
- We propose a training-free guidance framework that enforces multi-view consistency during the image editing process.
Why it matters
The importance of “3D-Consistent Multi-View Editing by Correspondence Guidance” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments