TDiR: Transformer based Diffusion for Image Restoration Tasks

TL;DR

This paper introduces TDiR, a transformer-based diffusion model that significantly enhances degraded images in challenging environments, outperforming existing methods in underwater image enhancement, denoising, and deraining tasks.

Contribution

The paper presents a novel transformer-based diffusion approach for image restoration, demonstrating superior performance over existing deep learning methods across multiple image quality metrics.

Findings

Outperforms existing methods in underwater image enhancement.

Achieves higher quality metrics in denoising and deraining.

Proves the effectiveness of diffusion models combined with transformers.

Abstract

Images captured in challenging environments often experience various forms of degradation, including noise, color cast, blur, and light scattering. These effects significantly reduce image quality, hindering their applicability in downstream tasks such as object detection, mapping, and classification. Our transformer-based diffusion model was developed to address image restoration tasks, aiming to improve the quality of degraded images. This model was evaluated against existing deep learning methodologies across multiple quality metrics for underwater image enhancement, denoising, and deraining on publicly available datasets. Our findings demonstrate that the diffusion model, combined with transformers, surpasses current methods in performance. The results of our model highlight the efficacy of diffusion models and transformers in improving the quality of degraded images, consequently expanding their utility in downstream tasks that require high-fidelity visual data.