# FUSE-Net: Multi-Scale CNN for NIR Band Prediction from RGB Using GNDVI-Guided Green Channel Enhancement

## TL;DR

This paper introduces a method to estimate near-infrared reflectance from standard RGB images using a green channel enhancement and a deep learning model, enabling cost-effective vegetation analysis.

## Contribution

The novel G-RGB method and FUSE-Net model enable accurate NIR band prediction from RGB images using GNDVI-guided enhancement and multi-scale CNNs.

## Key findings

- G-RGB input outperformed standard RGB in estimating NIR reflectance across multiple metrics.
- FUSE-Net achieved the best performance when used with G-RGB inputs in recovering spectral information.
- The method provides a cost-effective alternative to hyperspectral imaging for scenarios with limited access to HSI systems.

## Abstract

Hyperspectral imaging (HSI) is a powerful tool for precision imaging tasks such as vegetation analysis, but its widespread use remains limited due to the high cost of equipment and challenges in data acquisition. To explore a more accessible alternative, we propose a Green Normalized Difference Vegetation Index (GNDVI)-guided green channel adjustment method, termed G-RGB, which enables the estimation of near-infrared (NIR) reflectance from standard RGB image inputs. The G-RGB method enhances the green channel to encode NIR-like information, generating a spectrally enriched representation. Building on this, we introduce FUSE-Net, a novel deep learning model that combines multi-scale convolutional layers and MLP-Mixer-based channel learning to effectively model spatial and spectral dependencies. For evaluation, we constructed a high-resolution RGB-HSI paired dataset by capturing basil leaves under controlled conditions. Through ablation studies and band combination analysis, we assessed the model’s ability to recover spectral information. The experimental results showed that the G-RGB input consistently outperformed unmodified RGB across multiple metrics, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), spectral correlation coefficient (SCC), and structural similarity (SSIM), with the best performance observed when paired with FUSE-Net. While our method does not replace true NIR data, it offers a viable approximation during inference when only RGB images are available, supporting cost-effective analysis in scenarios where HSI systems are inaccessible.