# JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video

arXiv: https://arxiv.org/abs/1909.04391 · HTML: https://mlsanity.com/paper/1909.04391/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 30 of 31)

- [HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization](https://mlsanity.com/paper/2105.13084/) (2021)
- [HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset](https://mlsanity.com/paper/2103.14943/) (2021)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results](https://mlsanity.com/paper/2106.01439/) (2021)
- [A New Journey from SDRTV to HDRTV](https://mlsanity.com/paper/2108.07978/) (2021)
- [Text2Light: Zero-Shot Text-Driven HDR Panorama Generation](https://mlsanity.com/paper/2209.09898/) (2022)
- [GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild](https://mlsanity.com/paper/2211.12352/) (2022)
- [Efficient Image Generation with Variadic Attention Heads](https://mlsanity.com/paper/2211.05770/) (2022)
- [SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss](https://mlsanity.com/paper/2109.15044/) (2021)
- [How to cheat with metrics in single-image HDR reconstruction](https://mlsanity.com/paper/2108.08713/) (2021)
- [Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models](https://mlsanity.com/paper/2303.13031/) (2023)
- [Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites](https://mlsanity.com/paper/2205.02031/) (2022)
- [AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results](https://mlsanity.com/paper/2508.13479/) (2025)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach](https://mlsanity.com/paper/2211.03058/) (2022)
- [Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation](https://mlsanity.com/paper/2309.04084/) (2023)
- [Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables](https://mlsanity.com/paper/2508.16121/) (2025)
- [Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmark](https://mlsanity.com/paper/2207.03367/) (2022)
- [DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2210.04429/) (2022)
- [Semantic decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation](https://mlsanity.com/paper/2208.06283/) (2022)
- [Global Priors Guided Modulation Network for Joint Super-Resolution and Inverse Tone-Mapping](https://mlsanity.com/paper/2208.06885/) (2022)
- [Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversion](https://mlsanity.com/paper/2411.10775/) (2024)
- [Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement](https://mlsanity.com/paper/2507.12135/) (2025)
- [Lightness Modulated Deep Inverse Tone Mapping](https://mlsanity.com/paper/2107.07907/) (2021)
- [EAA-Net: Rethinking the Autoencoder Architecture with Intra-class Features for Medical Image Segmentation](https://mlsanity.com/paper/2208.09197/) (2022)
- [A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU](https://mlsanity.com/paper/2303.08999/) (2023)
- [Lightweight Improved Residual Network for Efficient Inverse Tone Mapping](https://mlsanity.com/paper/2307.03998/) (2023)
- [Redistributing the Precision and Content in 3D-LUT-based Inverse Tone-mapping for HDR/WCG Display](https://mlsanity.com/paper/2309.17160/) (2023)
- [RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning](https://mlsanity.com/paper/2505.07322/) (2025)
- [Wavelet-Domain Masked Image Modeling for Color-Consistent HDR Video Reconstruction](https://mlsanity.com/paper/2602.07393/) (2026)

## Abstract (arXiv)

Joint learning of super-resolution (SR) and inverse tone-mapping (ITM) has been explored recently, to convert legacy low resolution (LR) standard dynamic range (SDR) videos to high resolution (HR) high dynamic range (HDR) videos for the growing need of UHD HDR TV/broadcasting applications. However, previous CNN-based methods directly reconstruct the HR HDR frames from LR SDR frames, and are only trained with a simple L2 loss. In this paper, we take a divide-and-conquer approach in designing a novel GAN-based joint SR-ITM network, called JSI-GAN, which is composed of three task-specific subnets: an image reconstruction subnet, a detail restoration (DR) subnet and a local contrast enhancement (LCE) subnet. We delicately design these subnets so that they are appropriately trained for the intended purpose, learning a pair of pixel-wise 1D separable filters via the DR subnet for detail restoration and a pixel-wise 2D local filter by the LCE subnet for contrast enhancement. Moreover, to train the JSI-GAN effectively, we propose a novel detail GAN loss alongside the conventional GAN loss, which helps enhancing both local details and contrasts to reconstruct high quality HR HDR results. When all subnets are jointly trained well, the predicted HR HDR results of higher quality are obtained with at least 0.41 dB gain in PSNR over those generated by the previous methods.