MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields
This addresses the challenge of intrinsic image decomposition for real-world scenes, enabling better image editing applications, though it appears incremental by building on NeRF with multi-light integration.
The paper tackles the problem of extracting intrinsic image components like reflectance and shading from real-world scenes, which existing methods struggle with, by proposing MLI-NeRF that uses multiple light information to generate pseudo-labels and outperforms state-of-the-art methods on synthetic and real-world datasets.
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.