MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields

TL;DR

MLI-NeRF introduces a novel approach that leverages multiple light sources within neural radiance fields to improve intrinsic image decomposition, achieving better results on synthetic and real-world data without ground truth labels.

Contribution

It integrates multi-light information into NeRFs for intrinsic decomposition, providing a simple supervision method that enhances robustness and generalization across scene types.

Findings

Outperforms existing state-of-the-art methods on synthetic datasets.

Effective on real-world datasets with diverse scene types.

Enables applications in image editing tasks.

Abstract

Current methods for extracting intrinsic image components, such as reflectance and shading, primarily rely on statistical priors. These methods focus mainly on simple synthetic scenes and isolated objects and struggle to perform well on challenging real-world data. To address this issue, we propose MLI-NeRF, which integrates \textbf{M}ultiple \textbf{L}ight information in \textbf{I}ntrinsic-aware \textbf{Ne}ural \textbf{R}adiance \textbf{F}ields. By leveraging scene information provided by different light source positions complementing the multi-view information, we generate pseudo-label images for reflectance and shading to guide intrinsic image decomposition without the need for ground truth data. Our method introduces straightforward supervision for intrinsic component separation and ensures robustness across diverse scene types. We validate our approach on both synthetic and real-world datasets, outperforming existing state-of-the-art methods. Additionally, we demonstrate its applicability to various image editing tasks. The code and data are publicly available.