mlsanityData to 7 Oct 2026

DRHDR: A Dual branch Residual Network for Multi-Bracket High Dynamic Range Imaging

arXiv 2206.04124 ↗First posted 8 Jun 2022cs.CV eess.IVcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce DRHDR, a Dual branch Residual Convolutional Neural Network for Multi-Bracket HDR Imaging. To address the challenges of fusing multiple brackets from dynamic scenes, we propose an efficient dual branch network that operates on two different resolutions. The full resolution branch uses a Deformable Convolutional Block to align features and retain high-frequency details. A low resolution branch with a Spatial Attention Block aims to attend wanted areas from the non-reference brackets, and suppress displaced features that could incur on ghosting artifacts. By using a dual branch approach we are able to achieve high quality results while constraining the computational resources required to estimate the HDR results.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 34 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

18 of 34 references.

References · 18

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  5. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  6. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  7. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  8. 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 116
  9. 2020DeepLPF: Deep Local Parametric Filters for Image Enhancementcited by 107
  10. 2017Deep High Dynamic Range Imaging with Large Foreground Motionscited by 98
  11. 2020HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motionscited by 80
  12. 2017DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairscited by 77
6 more
  1. 2021ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imagingcited by 51
  2. 2020Spatially-Adaptive Pixelwise Networks for Fast Image Translationcited by 45
  3. 2021NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Resultscited by 36
  4. 2022FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imagingcited by 17
  5. 2022NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Resultscited by 10
  6. 2020Learning a Reinforced Agent for Flexible Exposure Bracketing Selectioncited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023Frame-Event Alignment and Fusion Network for High Frame Rate Trackingcited by 43
  2. 2024PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignmentcited by 2
  3. 2023High Dynamic Range Imaging via Visual Attention Modulescited by 0