SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field
This work addresses the problem of improving rendering quality for computer graphics and vision applications, but it appears incremental as it builds on existing NeRF methods with spectral modifications.
The paper tackles the problem of high-quality physically based rendering by proposing SpectralNeRF, an end-to-end Neural Radiance Field architecture that modifies classical spectral rendering into two steps for generating spectrum maps and combining them into RGB output, with experimental results showing it is superior to recent NeRF-based methods on synthetic and real datasets.
In this paper, we propose SpectralNeRF, an end-to-end Neural Radiance Field (NeRF)-based architecture for high-quality physically based rendering from a novel spectral perspective. We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum maps for the RGB output. Our SpectralNeRF follows these two steps through the proposed multi-layer perceptron (MLP)-based architecture (SpectralMLP) and Spectrum Attention UNet (SAUNet). Given the ray origin and the ray direction, the SpectralMLP constructs the spectral radiance field to obtain spectrum maps of novel views, which are then sent to the SAUNet to produce RGB images of white-light illumination. Applying NeRF to build up the spectral rendering is a more physically-based way from the perspective of ray-tracing. Further, the spectral radiance fields decompose difficult scenes and improve the performance of NeRF-based methods. Comprehensive experimental results demonstrate the proposed SpectralNeRF is superior to recent NeRF-based methods when synthesizing new views on synthetic and real datasets. The codes and datasets are available at https://github.com/liru0126/SpectralNeRF.