English

Reference-guided Controllable Inpainting of Neural Radiance Fields

Computer Vision and Pattern Recognition 2023-04-21 v2

Abstract

The popularity of Neural Radiance Fields (NeRFs) for view synthesis has led to a desire for NeRF editing tools. Here, we focus on inpainting regions in a view-consistent and controllable manner. In addition to the typical NeRF inputs and masks delineating the unwanted region in each view, we require only a single inpainted view of the scene, i.e., a reference view. We use monocular depth estimators to back-project the inpainted view to the correct 3D positions. Then, via a novel rendering technique, a bilateral solver can construct view-dependent effects in non-reference views, making the inpainted region appear consistent from any view. For non-reference disoccluded regions, which cannot be supervised by the single reference view, we devise a method based on image inpainters to guide both the geometry and appearance. Our approach shows superior performance to NeRF inpainting baselines, with the additional advantage that a user can control the generated scene via a single inpainted image. Project page: https://ashmrz.github.io/reference-guided-3d

Keywords

Cite

@article{arxiv.2304.09677,
  title  = {Reference-guided Controllable Inpainting of Neural Radiance Fields},
  author = {Ashkan Mirzaei and Tristan Aumentado-Armstrong and Marcus A. Brubaker and Jonathan Kelly and Alex Levinshtein and Konstantinos G. Derpanis and Igor Gilitschenski},
  journal= {arXiv preprint arXiv:2304.09677},
  year   = {2023}
}

Comments

Project Page: https://ashmrz.github.io/reference-guided-3d