# AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring

arXiv: https://arxiv.org/abs/2406.09135 · HTML: https://mlsanity.com/paper/2406.09135/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 46 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [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)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [The Reversible Residual Network: Backpropagation Without Storing Activations](https://mlsanity.com/paper/1707.04585/) (2017)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Stripformer: Strip Transformer for Fast Image Deblurring](https://mlsanity.com/paper/2204.04627/) (2022)
- [i-RevNet: Deep Invertible Networks](https://mlsanity.com/paper/1802.07088/) (2018)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)

## Built on by (most cited first, 25 of 25)

- [LoFormer: Local Frequency Transformer for Image Deblurring](https://mlsanity.com/paper/2407.16993/) (2024)
- [NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results](https://mlsanity.com/paper/2504.12401/) (2025)
- [One-Step Diffusion Model for Image Motion-Deblurring](https://mlsanity.com/paper/2503.06537/) (2025)
- [FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring](https://mlsanity.com/paper/2510.01641/) (2025)
- [DPMambaIR: All-in-One Image Restoration via Degradation-Aware Prompt State Space Model](https://mlsanity.com/paper/2504.17732/) (2025)
- [F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring](https://mlsanity.com/paper/2409.02056/) (2024)
- [Efficient RAW Image Deblurring with Adaptive Frequency Modulation](https://mlsanity.com/paper/2505.24407/) (2025)
- [MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration](https://mlsanity.com/paper/2509.06803/) (2025)
- [Beyond the Ground Truth: Enhanced Supervision for Image Restoration](https://mlsanity.com/paper/2512.03932/) (2025)
- [Moment-Reenacting: Inverse Motion Degradation with Cross-shutter Guidance](https://mlsanity.com/paper/2605.22423/) (2026)
- [SloMoDeblur: A Large-Scale Smartphone Image Deblurring Dataset](https://mlsanity.com/paper/2506.19445/) (2025)
- [Towards Differential Handling of Various Blur Regions for Accurate Image Deblurring](https://mlsanity.com/paper/2502.19677/) (2025)
- [Adaptive Identification of Blurred Regions for Accurate Image Deblurring](https://mlsanity.com/paper/2502.20880/) (2025)
- [Motion-Aware Adaptive Pixel Pruning for Efficient Local Motion Deblurring](https://mlsanity.com/paper/2507.07708/) (2025)
- [Learning to Restore Multi-Degraded Images via Ingredient Decoupling and Task-Aware Path Adaptation](https://mlsanity.com/paper/2511.04920/) (2025)
- [Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution](https://mlsanity.com/paper/2511.10166/) (2025)
- [DeepRFTv2: Kernel-level Learning for Image Deblurring](https://mlsanity.com/paper/2511.21132/) (2025)
- [A low-complexity method for efficient depth-guided image deblurring](https://mlsanity.com/paper/2601.03924/) (2026)
- [From Physical Degradation Models to Task-Aware All-in-One Image Restoration](https://mlsanity.com/paper/2601.10192/) (2026)
- [Improving Image-to-Image Translation via a Rectified Flow Reformulation](https://mlsanity.com/paper/2603.20186/) (2026)
- [Saturation-Aware Space-Variant Blind Image Deblurring](https://mlsanity.com/paper/2604.16200/) (2026)
- [Restoration-Aligned Generative Flow Models for Blind Motion Deblurring](https://mlsanity.com/paper/2605.08854/) (2026)
- [CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion](https://mlsanity.com/paper/2606.30030/) (2026)
- [Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring](https://mlsanity.com/paper/2607.00251/) (2026)
- [PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video](https://mlsanity.com/paper/2610.01279/) (2026)

## Abstract (arXiv)

Despite the recent progress in enhancing the efficacy of image deblurring, the limited decoding capability constrains the upper limit of State-Of-The-Art (SOTA) methods. This paper proposes a pioneering work, Adaptive Patch Exiting Reversible Decoder (AdaRevD), to explore their insufficient decoding capability. By inheriting the weights of the well-trained encoder, we refactor a reversible decoder which scales up the single-decoder training to multi-decoder training while remaining GPU memory-friendly. Meanwhile, we show that our reversible structure gradually disentangles high-level degradation degree and low-level blur pattern (residual of the blur image and its sharp counterpart) from compact degradation representation. Besides, due to the spatially-variant motion blur kernels, different blur patches have various deblurring difficulties. We further introduce a classifier to learn the degradation degree of image patches, enabling them to exit at different sub-decoders for speedup. Experiments show that our AdaRevD pushes the limit of image deblurring, e.g., achieving 34.60 dB in PSNR on GoPro dataset.