# Wavelet-Based Network For High Dynamic Range Imaging

arXiv: https://arxiv.org/abs/2108.01434 · HTML: https://mlsanity.com/paper/2108.01434/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 56 references that are in the map.
- First posted on arXiv 3 Aug 2021.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [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)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Wavelet-Based Dual-Branch Network for Image Demoireing](https://mlsanity.com/paper/2007.07173/) (2020)
- [NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results](https://mlsanity.com/paper/2005.04117/) (2020)
- [Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networks](https://mlsanity.com/paper/1809.06647/) (2018)
- [Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification](https://mlsanity.com/paper/1611.06345/) (2016)
- [Locally Non-rigid Registration for Mobile HDR Photography](https://mlsanity.com/paper/1504.01441/) (2015)

## Built on by (most cited first, 9 of 9)

- [TAPE: Task-Agnostic Prior Embedding for Image Restoration](https://mlsanity.com/paper/2203.06074/) (2022)
- [Low-Light Video Enhancement with Synthetic Event Guidance](https://mlsanity.com/paper/2208.11014/) (2022)
- [SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers](https://mlsanity.com/paper/2112.09426/) (2021)
- [HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains](https://mlsanity.com/paper/2304.04773/) (2023)
- [IFT: Image Fusion Transformer for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/2309.15019/) (2023)
- [PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment](https://mlsanity.com/paper/2403.10376/) (2024)
- [SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes](https://mlsanity.com/paper/2206.09611/) (2022)
- [High Dynamic Range Imaging via Visual Attention Modules](https://mlsanity.com/paper/2307.14705/) (2023)
- [FSB-Net: Frequency-Spatial Boundary Network for Brain Stroke Lesion Segmentation in Non-Contrast CT](https://mlsanity.com/paper/2607.20955/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly high-frequency signals. In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequency-guided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multi-frame HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-of-the-art performance.