Decomposing NeRF for Editing via Feature Field Distillation

TL;DR

This paper introduces a method to decompose NeRFs into semantic regions using distilled 3D feature fields from 2D vision models, enabling targeted editing without retraining.

Contribution

It proposes a novel approach to semantically decompose NeRFs via feature field distillation, facilitating query-based local editing of 3D scenes.

Findings

Distilled feature fields enable effective 3D scene segmentation.

The method allows semantic editing based on text, images, or clicks.

It transfers 2D vision and language models to 3D scene editing.

Abstract

Emerging neural radiance fields (NeRF) are a promising scene representation for computer graphics, enabling high-quality 3D reconstruction and novel view synthesis from image observations. However, editing a scene represented by a NeRF is challenging, as the underlying connectionist representations such as MLPs or voxel grids are not object-centric or compositional. In particular, it has been difficult to selectively edit specific regions or objects. In this work, we tackle the problem of semantic scene decomposition of NeRFs to enable query-based local editing of the represented 3D scenes. We propose to distill the knowledge of off-the-shelf, self-supervised 2D image feature extractors such as CLIP-LSeg or DINO into a 3D feature field optimized in parallel to the radiance field. Given a user-specified query of various modalities such as text, an image patch, or a point-and-click selection, 3D feature fields semantically decompose 3D space without the need for re-training and enable us to semantically select and edit regions in the radiance field. Our experiments validate that the distilled feature fields (DFFs) can transfer recent progress in 2D vision and language foundation models to 3D scene representations, enabling convincing 3D segmentation and selective editing of emerging neural graphics representations.