# FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network

arXiv: https://arxiv.org/abs/1912.11463 · HTML: https://mlsanity.com/paper/1912.11463/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2019.

## Built on by (most cited first, 22 of 22)

- [HDR-NeRF: High Dynamic Range Neural Radiance Fields](https://mlsanity.com/paper/2111.14451/) (2021)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting](https://mlsanity.com/paper/2405.15125/) (2024)
- [Single-Image HDR Reconstruction by Multi-Exposure Generation](https://mlsanity.com/paper/2210.15897/) (2022)
- [How to cheat with metrics in single-image HDR reconstruction](https://mlsanity.com/paper/2108.08713/) (2021)
- [A Two-stage Deep Network for High Dynamic Range Image Reconstruction](https://mlsanity.com/paper/2104.09386/) (2021)
- [HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN](https://mlsanity.com/paper/2110.01660/) (2021)
- [LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN](https://mlsanity.com/paper/2211.11270/) (2022)
- [Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning](https://mlsanity.com/paper/2303.07327/) (2023)
- [HDR Reconstruction from Bracketed Exposures and Events](https://mlsanity.com/paper/2203.14825/) (2022)
- [ArtHDR-Net: Perceptually Realistic and Accurate HDR Content Creation](https://mlsanity.com/paper/2309.03827/) (2023)
- [GTA-HDR: A Large-Scale Synthetic Dataset for HDR Image Reconstruction](https://mlsanity.com/paper/2403.17837/) (2024)
- [Physically Inspired Dense Fusion Networks for Relighting](https://mlsanity.com/paper/2105.02209/) (2021)
- [DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction](https://mlsanity.com/paper/2210.04429/) (2022)
- [CEN-HDR: Computationally Efficient neural Network for real-time High Dynamic Range imaging](https://mlsanity.com/paper/2302.05213/) (2023)
- [Deep Dynamic Cloud Lighting](https://mlsanity.com/paper/2304.09317/) (2023)
- [HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation](https://mlsanity.com/paper/2402.06692/) (2024)
- [Single-Image HDR Reconstruction Assisted Ghost Suppression and Detail Preservation Network for Multi-Exposure HDR Imaging](https://mlsanity.com/paper/2403.04228/) (2024)
- [A Mixed Quantization Network for Computationally Efficient Mobile Inverse Tone Mapping](https://mlsanity.com/paper/2203.06504/) (2022)
- [A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstruction](https://mlsanity.com/paper/2410.15068/) (2024)
- [HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion](https://mlsanity.com/paper/2602.19706/) (2026)
- [InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstruction](https://mlsanity.com/paper/2603.11298/) (2026)

## Abstract (arXiv)

High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning. Various feed-forward Convolutional Neural Networks (CNNs) have been proposed for learning LDR to HDR representations. To better utilize the power of CNNs, we exploit the idea of feedback, where the initial low level features are guided by the high level features using a hidden state of a Recurrent Neural Network. Unlike a single forward pass in a conventional feed-forward network, the reconstruction from LDR to HDR in a feedback network is learned over multiple iterations. This enables us to create a coarse-to-fine representation, leading to an improved reconstruction at every iteration. Various advantages over standard feed-forward networks include early reconstruction ability and better reconstruction quality with fewer network parameters. We design a dense feedback block and propose an end-to-end feedback network- FHDR for HDR image generation from a single exposure LDR image. Qualitative and quantitative evaluations show the superiority of our approach over the state-of-the-art methods.