# X-DECODE: EXtreme Deblurring with Curriculum Optimization and Domain Equalization

arXiv: https://arxiv.org/abs/2504.08072 · HTML: https://mlsanity.com/paper/2504.08072/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Event-Based Fusion for Motion Deblurring with Cross-modal Attention](https://mlsanity.com/paper/2112.00167/) (2021)
- [Automatic CNN-based detection of cardiac MR motion artefacts using k-space data augmentation and curriculum learning](https://mlsanity.com/paper/1810.12185/) (2018)
- [ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation](https://mlsanity.com/paper/2312.10998/) (2023)
- [Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring](https://mlsanity.com/paper/2406.07551/) (2024)

## Abstract (arXiv)

Restoring severely blurred images remains a significant challenge in computer vision, impacting applications in autonomous driving, medical imaging, and photography. This paper introduces a novel training strategy based on curriculum learning to improve the robustness of deep learning models for extreme image deblurring. Unlike conventional approaches that train on only low to moderate blur levels, our method progressively increases the difficulty by introducing images with higher blur severity over time, allowing the model to adapt incrementally. Additionally, we integrate perceptual and hinge loss during training to enhance fine detail restoration and improve training stability. We experimented with various curriculum learning strategies and explored the impact of the train-test domain gap on the deblurring performance. Experimental results on the Extreme-GoPro dataset showed that our method outperforms the next best method by 14% in SSIM, whereas experiments on the Extreme-KITTI dataset showed that our method outperforms the next best by 18% in SSIM. Ablation studies showed that a linear curriculum progression outperforms step-wise, sigmoid, and exponential progressions, while hyperparameter settings such as the training blur percentage and loss function formulation all play important roles in addressing extreme blur artifacts. Datasets and code are available at https://github.com/RAPTOR-MSSTATE/XDECODE