Existing methods for spectral reconstruction usually learn a discrete mapping
from RGB images to a number of spectral bands. However, this modeling strategy
ignores the continuous nature of spectral signature. In this paper, we propose
Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a
novel continuous spectral representation. To this end, we embrace the concept
of implicit function and implement a parameterized embodiment with a neural
network. Specifically, we first adopt a backbone network to extract spatial
features of RGB inputs. Based on it, we devise Spectral Profile Interpolation
(SPI) module and Neural Attention Mapping (NAM) module to enrich deep features,
where the spatial-spectral correlation is involved for a better representation.
Then, we view the number of sampled spectral bands as the coordinate of
continuous implicit function, so as to learn the projection from deep features
to spectral intensities. Extensive experiments demonstrate the distinct
advantage of NeSR in reconstruction accuracy over baseline methods. Moreover,
NeSR extends the flexibility of spectral reconstruction by enabling an
arbitrary number of spectral bands as the target output.

本文介绍了 Neural Spectral Reconstruction (NeSR) 方法来提高光谱重建的连续性。通过引入一种新的连续光谱表示，我们利用神经网络实现了参数化拟合。经过实验验证，NeSR 方法在重建准确性方面表现出明显优势，同时也可以支持任意数量的光谱重建。