mlsanityData to 7 Oct 2026

LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN

arXiv 2211.11270 ↗First posted 21 Nov 2022cs.CV cs.MMcited by 6

Not on the map. Why?

Abstract (arXiv)

High dynamic range (HDR) image is widely-used in graphics and photography due to the rich information it contains. Recently the community has started using deep neural network (DNN) to reconstruct standard dynamic range (SDR) images into HDR. Albeit the superiority of current DNN-based methods, their application scenario is still limited: (1) heavy model impedes real-time processing, and (2) inapplicable to legacy SDR content with more degradation types. Therefore, we propose a lightweight DNN-based method trained to tackle legacy SDR. For better design, we reform the problem modeling and emphasize degradation model. Experiments show that our method reached appealing performance with minimal computational cost compared with others.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 31 of its 63 references that are in the map. First posted on arXiv 21 Nov 2022.

Builds on

31 of 63 references.

References · 31

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  3. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  4. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  5. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  6. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
  7. 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 116
  8. 2017Deep High Dynamic Range Imaging with Large Foreground Motionscited by 98
  9. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  10. 2021Towards Flexible Blind JPEG Artifacts Removalcited by 76
  11. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  12. 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
19 more
  1. 2021HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Datasetcited by 45
  2. 2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
  3. 2020AIM 2020 Challenge on Efficient Super-Resolution: Methods and Resultscited by 36
  4. 2021NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Resultscited by 36
  5. 2017Learning High Dynamic Range from Outdoor Panoramascited by 34
  6. 2018Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Imagecited by 25
  7. 2019FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Networkcited by 22
  8. 2021Luminance Attentive Networks for HDR Image and Panorama Reconstructioncited by 18
  9. 2021Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 15
  10. 2021Very Lightweight Photo Retouching Network with Conditional Sequential Modulationcited by 14
  11. 2021How to cheat with metrics in single-image HDR reconstructioncited by 11
  12. 2021A Two-stage Deep Network for High Dynamic Range Image Reconstructioncited by 10
  13. 2022NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Resultscited by 10
  14. 2018Hybrid Loss for Learning Single-Image-based HDR Reconstructioncited by 7
  15. 2021HDR-cGAN: Single LDR to HDR Image Translation using Conditional GANcited by 7
  16. 2021Deep HDR Hallucination for Inverse Tone Mappingcited by 5
  17. 2019Joint High Dynamic Range Imaging and Super-Resolution from a Single Imagecited by 2
  18. 2022Unsupervised HDR Imaging: What Can Be Learned from a Single 8-bit Video?cited by 2
  19. 2021Lightness Modulated Deep Inverse Tone Mappingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 0; 2026: 2.

6 papers.

  1. 2023Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Modelscited by 11
  2. 2024Intrinsic Single-Image HDR Reconstructioncited by 11
  3. 2024HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translationcited by 3
  4. 2026DiffHDR: Re-Exposing LDR Videos with Video Diffusion Modelscited by 3
  5. 2024A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstructioncited by 0
  6. 2026Recurrent Dynamic Range Extensioncited by 0