RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Models

TL;DR

RePaint-NeRF introduces a method that uses semantic masks and diffusion models to enable flexible, high-quality editing of 3D scenes represented by Neural Radiance Fields, allowing modifications in appearance and shape guided by text prompts.

Contribution

The paper presents a novel framework combining diffusion models with NeRF for semantic-guided 3D content editing, enhancing editability and diversity.

Findings

Effective editing of 3D objects in NeRF using text prompts

Improved diversity and flexibility in 3D scene modifications

Validated on both real-world and synthetic datasets

Abstract

The emergence of Neural Radiance Fields (NeRF) has promoted the development of synthesized high-fidelity views of the intricate real world. However, it is still a very demanding task to repaint the content in NeRF. In this paper, we propose a novel framework that can take RGB images as input and alter the 3D content in neural scenes. Our work leverages existing diffusion models to guide changes in the designated 3D content. Specifically, we semantically select the target object and a pre-trained diffusion model will guide the NeRF model to generate new 3D objects, which can improve the editability, diversity, and application range of NeRF. Experiment results show that our algorithm is effective for editing 3D objects in NeRF under different text prompts, including editing appearance, shape, and more. We validate our method on both real-world datasets and synthetic-world datasets for these editing tasks. Please visit https://starstesla.github.io/repaintnerf for a better view of our results.