Raw Image Deblurring

TL;DR

This paper introduces a novel RAW image deblurring method, a new dataset, and demonstrates that RAW-based training improves deblurring performance, offering a promising direction for future research.

Contribution

The paper presents the first RAW image deblurring dataset and a new neural network model that leverages RAW image characteristics for superior deblurring results.

Findings

RAW-based models outperform sRGB-trained models

The new dataset enables better generalization across sensors

Existing models can be improved with RAW training

Abstract

Deep learning-based blind image deblurring plays an essential role in solving image blur since all existing kernels are limited in modeling the real world blur. Thus far, researchers focus on powerful models to handle the deblurring problem and achieve decent results. For this work, in a new aspect, we discover the great opportunity for image enhancement (e.g., deblurring) directly from RAW images and investigate novel neural network structures benefiting RAW-based learning. However, to the best of our knowledge, there is no available RAW image deblurring dataset. Therefore, we built a new dataset containing both RAW images and processed sRGB images and design a new model to utilize the unique characteristics of RAW images. The proposed deblurring model, trained solely from RAW images, achieves the state-of-art performance and outweighs those trained on processed sRGB images. Furthermore, with fine-tuning, the proposed model, trained on our new dataset, can generalize to other sensors. Additionally, by a series of experiments, we demonstrate that existing deblurring models can also be improved by training on the RAW images in our new dataset. Ultimately, we show a new venue for further opportunities based on the devised novel raw-based deblurring method and the brand-new Deblur-RAW dataset.