# Progressive and Selective Fusion Network for High Dynamic Range Imaging

arXiv: https://arxiv.org/abs/2108.08585 · HTML: https://mlsanity.com/paper/2108.08585/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 19 Aug 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [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)

## Built on by (most cited first, 14 of 14)

- [Towards High-quality HDR Deghosting with Conditional Diffusion Models](https://mlsanity.com/paper/2311.00932/) (2023)
- [LEDiff: Latent Exposure Diffusion for HDR Generation](https://mlsanity.com/paper/2412.14456/) (2024)
- [A Unified HDR Imaging Method with Pixel and Patch Level](https://mlsanity.com/paper/2304.06943/) (2023)
- [SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders](https://mlsanity.com/paper/2304.06914/) (2023)
- [CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging](https://mlsanity.com/paper/2302.05213/) (2023)
- [Robust estimation of exposure ratios in multi-exposure image stacks](https://mlsanity.com/paper/2308.02968/) (2023)
- [PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment](https://mlsanity.com/paper/2403.10376/) (2024)
- [DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models](https://mlsanity.com/paper/2604.06161/) (2026)
- [S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion](https://mlsanity.com/paper/2504.07667/) (2025)
- [F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling](https://mlsanity.com/paper/2603.14920/) (2026)
- [Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging](https://mlsanity.com/paper/2207.02539/) (2022)
- [Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2208.02448/) (2022)
- [A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction](https://mlsanity.com/paper/2410.15068/) (2024)
- [Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping](https://mlsanity.com/paper/2608.05626/) (2026)

## Abstract (arXiv)

This paper considers the problem of generating an HDR image of a scene from its LDR images. Recent studies employ deep learning and solve the problem in an end-to-end fashion, leading to significant performance improvements. However, it is still hard to generate a good quality image from LDR images of a dynamic scene captured by a hand-held camera, e.g., occlusion due to the large motion of foreground objects, causing ghosting artifacts. The key to success relies on how well we can fuse the input images in their feature space, where we wish to remove the factors leading to low-quality image generation while performing the fundamental computations for HDR image generation, e.g., selecting the best-exposed image/region. We propose a novel method that can better fuse the features based on two ideas. One is multi-step feature fusion; our network gradually fuses the features in a stack of blocks having the same structure. The other is the design of the component block that effectively performs two operations essential to the problem, i.e., comparing and selecting appropriate images/regions. Experimental results show that the proposed method outperforms the previous state-of-the-art methods on the standard benchmark tests.