# Raw Image Deblurring

arXiv: https://arxiv.org/abs/2012.04264 · HTML: https://mlsanity.com/paper/2012.04264/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 22 of 22)

- [Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset](https://mlsanity.com/paper/2209.12475/) (2022)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains](https://mlsanity.com/paper/2403.16205/) (2024)
- [T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing](https://mlsanity.com/paper/2106.02809/) (2021)
- [RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset](https://mlsanity.com/paper/2305.00767/) (2023)
- [Learning to See Low-Light Images via Feature Domain Adaptation](https://mlsanity.com/paper/2312.06723/) (2023)
- [Toward Efficient Deep Blind RAW Image Restoration](https://mlsanity.com/paper/2409.18204/) (2024)
- [Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection](https://mlsanity.com/paper/2303.13916/) (2023)
- [Beyond RGB: Adaptive Parallel Processing for RAW Object Detection](https://mlsanity.com/paper/2503.13163/) (2025)
- [Efficient HDR Reconstruction from Real-World Raw Images](https://mlsanity.com/paper/2306.10311/) (2023)
- [Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring](https://mlsanity.com/paper/2412.07256/) (2024)
- [Efficient RAW Image Deblurring with Adaptive Frequency Modulation](https://mlsanity.com/paper/2505.24407/) (2025)
- [Learning to Jointly Deblur, Demosaick and Denoise Raw Images](https://mlsanity.com/paper/2104.06459/) (2021)
- [Towards Real-World Video Deblurring by Exploring Blur Formation Process](https://mlsanity.com/paper/2208.13184/) (2022)
- [FMD-cGAN: Fast Motion Deblurring using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2111.15438/) (2021)
- [Network state Estimation using Raw Video Analysis: vQoS-GAN based non-intrusive Deep Learning Approach](https://mlsanity.com/paper/2204.07062/) (2022)
- [Raw Instinct: Trust Your Classifiers and Skip the Conversion](https://mlsanity.com/paper/2403.14439/) (2024)
- [Uni-ISP: Toward Unifying the Learning of ISPs from Multiple Mobile Cameras](https://mlsanity.com/paper/2406.01003/) (2024)
- [BluRef: Unsupervised Image Deblurring with Dense-Matching References](https://mlsanity.com/paper/2603.14176/) (2026)
- [FreqAdapt: Frequency-Adaptive Processing for RAW Object Detection](https://mlsanity.com/paper/2608.03385/) (2026)
- [Binarized High-Efficiency RAW Video Restoration and Beyond](https://mlsanity.com/paper/2608.16756/) (2026)
- [Benchmarking RAW and RGB Restoration in Image Signal Processors](https://mlsanity.com/paper/2609.02831/) (2026)

## Abstract (arXiv)

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.