NeRF-Editing: Geometry Editing of Neural Radiance Fields

TL;DR

This paper introduces a novel method for controllable shape deformation of neural radiance fields (NeRFs) that allows users to modify scene geometry directly and generate new views without retraining.

Contribution

It establishes a correspondence between explicit mesh and implicit neural representations, enabling user-driven mesh deformation to edit scenes in NeRFs.

Findings

Effective shape deformation on synthetic scenes

Successful editing of real captured scenes

No retraining required for scene modifications

Abstract

Implicit neural rendering, especially Neural Radiance Field (NeRF), has shown great potential in novel view synthesis of a scene. However, current NeRF-based methods cannot enable users to perform user-controlled shape deformation in the scene. While existing works have proposed some approaches to modify the radiance field according to the user's constraints, the modification is limited to color editing or object translation and rotation. In this paper, we propose a method that allows users to perform controllable shape deformation on the implicit representation of the scene, and synthesizes the novel view images of the edited scene without re-training the network. Specifically, we establish a correspondence between the extracted explicit mesh representation and the implicit neural representation of the target scene. Users can first utilize well-developed mesh-based deformation methods to deform the mesh representation of the scene. Our method then utilizes user edits from the mesh representation to bend the camera rays by introducing a tetrahedra mesh as a proxy, obtaining the rendering results of the edited scene. Extensive experiments demonstrate that our framework can achieve ideal editing results not only on synthetic data, but also on real scenes captured by users.