mlsanityData to 7 Oct 2026

Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

arXiv 2307.03998 ↗First posted 8 Jul 2023cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 81 references that are in the map. First posted on arXiv 8 Jul 2023.

Builds on

44 of 81 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  8. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  9. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  10. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  11. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  12. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
32 more
  1. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  2. 2019Lightweight Image Super-Resolution with Information Multi-distillation Networkcited by 227
  3. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  4. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  5. 2020Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timecited by 163
  6. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
  7. 2020Residual Feature Distillation Network for Lightweight Image Super-Resolutioncited by 122
  8. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  9. 2021SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentationcited by 87
  10. 2021ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristiccited by 81
  11. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  12. 2020Conditional Sequential Modulation for Efficient Global Image Retouchingcited by 71
  13. 2021High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Networkcited by 61
  14. 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
  15. 2021Temporal Modulation Network for Controllable Space-Time Video Super-Resolutioncited by 54
  16. 2023A Dynamic Multi-Scale Voxel Flow Network for Video Predictioncited by 53
  17. 2019Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applicationscited by 39
  18. 2021TF-Blender: Temporal Feature Blender for Video Object Detectioncited by 37
  19. 2020DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregationcited by 33
  20. 2023TransFlow: Transformer as Flow Learnercited by 32
  21. 2019JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Videocited by 31
  22. 2021A New Journey from SDRTV to HDRTVcited by 30
  23. 2019DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factorscited by 24
  24. 2021Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restorationcited by 23
  25. 2021A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolutioncited by 19
  26. 2022High Dynamic Range and Super-Resolution from Raw Image Burstscited by 18
  27. 2018DYAN: A Dynamical Atoms-Based Network for Video Predictioncited by 11
  28. 2021Hierarchical Attention Fusion for Geo-Localizationcited by 9
  29. 2022Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolutioncited by 9
  30. 2022Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approachcited by 4
  31. 2022Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmarkcited by 3
  32. 2019Deep Robotic Prediction with hierarchical RGB-D Fusioncited by 1

Built on by

Not cited yet.