# Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network

arXiv: https://arxiv.org/abs/2204.09213 · HTML: https://mlsanity.com/paper/2204.09213/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content](https://mlsanity.com/paper/1803.02266/) (2018)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization](https://mlsanity.com/paper/2105.13084/) (2021)
- [Handheld Mobile Photography in Very Low Light](https://mlsanity.com/paper/1910.11336/) (2019)
- [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2105.10697/) (2021)
- [Image Correction via Deep Reciprocating HDR Transformation](https://mlsanity.com/paper/1804.04371/) (2018)
- [FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging](https://mlsanity.com/paper/2201.02625/) (2022)
- [A Two-stage Deep Network for High Dynamic Range Image Reconstruction](https://mlsanity.com/paper/2104.09386/) (2021)
- [Feature-Align Network with Knowledge Distillation for Efficient Denoising](https://mlsanity.com/paper/2103.01524/) (2021)

## Built on by (most cited first, 5 of 5)

- [PromptCIR: Blind Compressed Image Restoration with Prompt Learning](https://mlsanity.com/paper/2404.17433/) (2024)
- [NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results](https://mlsanity.com/paper/2205.12633/) (2022)
- [CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging](https://mlsanity.com/paper/2302.05213/) (2023)
- [High Dynamic Range Imaging via Visual Attention Modules](https://mlsanity.com/paper/2307.14705/) (2023)
- [Multi-Exposure Image Fusion via Distilled 3D LUT Grid with Editable Mode](https://mlsanity.com/paper/2412.13749/) (2024)

## Abstract (arXiv)

HDR is an important part of computational photography technology. In this paper, we propose a lightweight neural network called Efficient Attention-and-alignment-guided Progressive Network (EAPNet) for the challenge NTIRE 2022 HDR Track 1 and Track 2. We introduce a multi-dimensional lightweight encoding module to extract features. Besides, we propose Progressive Dilated U-shape Block (PDUB) that can be a progressive plug-and-play module for dynamically tuning MAccs and PSNR. Finally, we use fast and low-power feature-align module to deal with misalignment problem in place of the time-consuming Deformable Convolutional Network (DCN). The experiments show that our method achieves about 20 times compression on MAccs with better mu-PSNR and PSNR compared to the state-of-the-art method. We got the second place of both two tracks during the testing phase. Figure1. shows the visualized result of NTIRE 2022 HDR challenge.