IE-NeRF: Inpainting Enhanced Neural Radiance Fields in the Wild

TL;DR

This paper introduces IE-NeRF, an enhanced neural radiance field model that incorporates inpainting techniques to better handle transient objects in uncontrolled, real-world scenes, improving the quality of synthesized novel views.

Contribution

The paper proposes a novel inpainting-based extension to NeRF that explicitly models transient objects and occlusions, enabling more realistic view synthesis in dynamic scenes.

Findings

Achieves state-of-the-art results on landmark photo collections

Effectively excludes transient occlusions for clearer rendering

Improves volume rendering quality in uncontrolled environments

Abstract

We present a novel approach for synthesizing realistic novel views using Neural Radiance Fields (NeRF) with uncontrolled photos in the wild. While NeRF has shown impressive results in controlled settings, it struggles with transient objects commonly found in dynamic and time-varying scenes. Our framework called \textit{Inpainting Enhanced NeRF}, or \ours, enhances the conventional NeRF by drawing inspiration from the technique of image inpainting. Specifically, our approach extends the Multi-Layer Perceptrons (MLP) of NeRF, enabling it to simultaneously generate intrinsic properties (static color, density) and extrinsic transient masks. We introduce an inpainting module that leverages the transient masks to effectively exclude occlusions, resulting in improved volume rendering quality. Additionally, we propose a new training strategy with frequency regularization to address the sparsity issue of low-frequency transient components. We evaluate our approach on internet photo collections of landmarks, demonstrating its ability to generate high-quality novel views and achieve state-of-the-art performance.