# Dataset of scattered images using noncoherent light under varying diffusion conditions and projected patterns

## TL;DR

This paper introduces a dataset of scattered images captured with a low-cost optical system, useful for training and testing image restoration models in complex optical conditions.

## Contribution

The novelty lies in providing a diverse, open-source dataset of scattered images with ground truth for deep learning research in optics.

## Key findings

- The dataset includes scattered images and original patterns for various scattering conditions.
- It supports deep learning research for image recovery in scattering environments.
- The system uses diverse patterns and optical diffusers to enhance variability and generalization.

## Abstract

This data article presents an experimental dataset of scattered images, obtained using a low-cost, open-source, Raspberry Pi-based optical system. Each data sample includes two grayscale images of 256 × 256 resolution: the (i) scattered image, and (ii) original projected pattern as ground truth. The system projects diverse patterns using various optical diffusers with different scattering coefficients and physical thicknesses. The dataset includes geometric shapes, digits, and textures to increase variability and generalization. This variety allows the analysis of distinct scattering regimes and evaluation of image recovery models under varying optical complexities. The dataset supports deep learning research focused on inverse problems in optics. It is particularly useful for training and benchmarking image restoration models in scattering environments.