IE-NeRF: Inpainting Enhanced Neural Radiance Fields in the Wild
arXiv:2407.10695 · doi:10.1016/j.neucom.2024.129112
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.
References in corpus (6)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- Neural 3D Reconstruction in the Wild
- NeRF-In: Free-Form NeRF Inpainting with RGB-D Priors
- Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild
- ID-NeRF: Indirect Diffusion-guided Neural Radiance Fields for Generalizable View Synthesis