mlsanityData to 7 Oct 2026

Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models

arXiv 2303.13031 ↗First posted 23 Mar 2023cs.MM cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

In media industry, the demand of SDR-to-HDRTV up-conversion arises when users possess HDR-WCG (high dynamic range-wide color gamut) TVs while most off-the-shelf footage is still in SDR (standard dynamic range). The research community has started tackling this low-level vision task by learning-based approaches. When applied to real SDR, yet, current methods tend to produce dim and desaturated result, making nearly no improvement on viewing experience. Different from other network-oriented methods, we attribute such deficiency to training set (HDR-SDR pair). Consequently, we propose new HDRTV dataset (dubbed HDRTV4K) and new HDR-to-SDR degradation models. Then, it's used to train a luminance-segmented network (LSN) consisting of a global mapping trunk, and two Transformer branches on bright and dark luminance range. We also update assessment criteria by tailored metrics and subjective experiment. Finally, ablation studies are conducted to prove the effectiveness. Our work is available at: https://github.com/AndreGuo/HDRTVDM.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 35 of its 84 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

35 of 84 references.

References · 35

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  3. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  4. 2017Deep Bilateral Learning for Real-Time Image Enhancementcited by 200
  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. 2019YouTube UGC Dataset for Video Compression Researchcited by 124
  8. 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 116
  9. 2017Deep High Dynamic Range Imaging with Large Foreground Motionscited by 98
  10. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  11. 2020HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motionscited by 80
  12. 2021Towards Flexible Blind JPEG Artifacts Removalcited by 76
23 more
  1. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  2. 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
  3. 2021HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Datasetcited by 45
  4. 2021Deep Learning for HDR Imaging: State-of-the-Art and Future Trendscited by 45
  5. 2019Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applicationscited by 39
  6. 2019JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Videocited by 31
  7. 2018Image Correction via Deep Reciprocating HDR Transformationcited by 30
  8. 2021A New Journey from SDRTV to HDRTVcited by 30
  9. 2021Degrade is Upgrade: Learning Degradation for Low-light Image Enhancementcited by 13
  10. 2022SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mappingcited by 13
  11. 2022Subjective Assessment of High Dynamic Range Videos Under Different Ambient Conditionscited by 12
  12. 2021How to cheat with metrics in single-image HDR reconstructioncited by 11
  13. 2022NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Resultscited by 10
  14. 2022Modular Degradation Simulation and Restoration for Under-Display Cameracited by 7
  15. 2018Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizercited by 6
  16. 2022LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNNcited by 6
  17. 2021Deep HDR Hallucination for Inverse Tone Mappingcited by 5
  18. 2022Distilling Style from Image Pairs for Global Forward and Inverse Tone Mappingcited by 5
  19. 2022SDRTV-to-HDRTV Conversion via Spatial-Temporal Feature Fusioncited by 4
  20. 2022Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approachcited by 4
  21. 2022Self-supervision versus synthetic datasets: which is the lesser evil in the context of video denoising?cited by 3
  22. 2022Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmarkcited by 3
  23. 2022Global Priors Guided Modulation Network for Joint Super-Resolution and Inverse Tone-Mappingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 4.

11 papers.

  1. 2024Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Networkcited by 14
  2. 2023Towards Efficient SDRTV-to-HDRTV by Learning from Image Formationcited by 4
  3. 2026DiffHDR: Re-Exposing LDR Videos with Video Diffusion Modelscited by 3
  4. 2024Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversioncited by 2
  5. 2025S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusioncited by 2
  6. 2026HDR Video Generation via Latent Alignment with Logarithmic Encodingcited by 2
  7. 2023Redistributing the Precision and Content in 3D-LUT-based Inverse Tone-mapping for HDR/WCG Displaycited by 0
  8. 2025High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithmcited by 0
  9. 2025RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learningcited by 0
  10. 2026Wavelet-Domain Masked Image Modeling for Color-Consistent HDR Video Reconstructioncited by 0
  11. 2026LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformerscited by 0