# Learning deep illumination-robust features from multispectral filter array images

Source: [Learning deep illumination-robust features from multispectral filter array images](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a01f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:41:42.944Z

Authors: Anis Amziane

Published: 2024-07-22T08:35:41.000Z

## Abstract

Multispectral (MS) snapshot cameras equipped with a MS filter array (MSFA), capture multiple spectral bands in a single shot, resulting in a raw mosaic image where each pixel holds only one channel value. The fully-defined MS image is estimated from the raw one through \\textit{demosaicing}, which inevitably introduces spatio-spectral artifacts. Moreover, training on fully-defined MS images can be computationally intensive, particularly with deep neural networks (DNNs), and may result in features lacking discrimination power due to suboptimal learning of spatio-spectral interactions. Furthermore, outdoor MS image acquisition occurs under varying lighting conditions, leading to illumination-dependent features. This paper presents an original approach to learn discriminant and illumination-robust features directly from raw images. It involves: \\textit{raw spectral constancy} to mitigate the impact of illumination, \\textit{MSFA-preserving} transformations suited for raw image augmentation to train DNNs on diverse raw textures, and \\textit{raw-mixing} to capture discriminant spatio-spectral interactions in raw images. Experiments on MS image classification show that our approach outperforms both handcrafted and recent deep learning-based methods, while also requiring significantly less computational effort. The source code is available at https://github.com/AnisAmziane/RawTexture.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.15472>)

[PDF](<https://arxiv.org/pdf/2407.15472.pdf>)
