# HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

arXiv: https://arxiv.org/abs/2105.13084 · HTML: https://mlsanity.com/paper/2105.13084/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [Neural Nearest Neighbors Networks](https://mlsanity.com/paper/1810.12575/) (2018)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [Conditional Sequential Modulation for Efficient Global Image Retouching](https://mlsanity.com/paper/2009.10390/) (2020)
- [Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers](https://mlsanity.com/paper/1904.08118/) (2019)
- [Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications](https://mlsanity.com/paper/1904.11176/) (2019)
- [JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video](https://mlsanity.com/paper/1909.04391/) (2019)
- [Very Lightweight Photo Retouching Network with Conditional Sequential Modulation](https://mlsanity.com/paper/2104.06279/) (2021)
- [A Little Bit More: Bitplane-Wise Bit-Depth Recovery](https://mlsanity.com/paper/2005.01091/) (2020)
- [Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1707.00116/) (2017)
- [Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination](https://mlsanity.com/paper/1803.01532/) (2018)

## Built on by (most cited first, 30 of 58)

- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2302.11831/) (2023)
- [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)
- [An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection](https://mlsanity.com/paper/2305.09999/) (2023)
- [RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image](https://mlsanity.com/paper/2309.02020/) (2023)
- [A New Journey from SDRTV to HDRTV](https://mlsanity.com/paper/2108.07978/) (2021)
- [Learning A Low-Level Vision Generalist via Visual Task Prompt](https://mlsanity.com/paper/2408.08601/) (2024)
- [MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results](https://mlsanity.com/paper/2209.07052/) (2022)
- [Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network](https://mlsanity.com/paper/2405.00244/) (2024)
- [Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision](https://mlsanity.com/paper/2504.04903/) (2025)
- [Under-Display Camera Image Restoration with Scattering Effect](https://mlsanity.com/paper/2308.04163/) (2023)
- [UDC-UNet: Under-Display Camera Image Restoration via U-Shape Dynamic Network](https://mlsanity.com/paper/2209.01809/) (2022)
- [Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models](https://mlsanity.com/paper/2303.13031/) (2023)
- [Intrinsic Single-Image HDR Reconstruction](https://mlsanity.com/paper/2409.13803/) (2024)
- [NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results](https://mlsanity.com/paper/2205.12633/) (2022)
- [Towards Image Ambient Lighting Normalization](https://mlsanity.com/paper/2403.18730/) (2024)
- [LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN](https://mlsanity.com/paper/2211.11270/) (2022)
- [Deep HDR Hallucination for Inverse Tone Mapping](https://mlsanity.com/paper/2106.09486/) (2021)
- [Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network](https://mlsanity.com/paper/2204.09213/) (2022)
- [Towards Efficient SDRTV-to-HDRTV by Learning from Image Formation](https://mlsanity.com/paper/2309.04084/) (2023)
- [HDRT: A Large-Scale Dataset for Infrared-Guided HDR Imaging](https://mlsanity.com/paper/2406.05475/) (2024)
- [Exploring Scalable Unified Modeling for General Low-Level Vision](https://mlsanity.com/paper/2507.14801/) (2025)
- [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)
- [Single-Image HDR Reconstruction Assisted Ghost Suppression and Detail Preservation Network for Multi-Exposure HDR Imaging](https://mlsanity.com/paper/2403.04228/) (2024)
- [HDR Imaging for Dynamic Scenes with Events](https://mlsanity.com/paper/2404.03210/) (2024)
- [Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior](https://mlsanity.com/paper/2406.09389/) (2024)
- [CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehicles](https://mlsanity.com/paper/2111.08243/) (2021)
- [Global Priors Guided Modulation Network for Joint Super-Resolution and Inverse Tone-Mapping](https://mlsanity.com/paper/2208.06885/) (2022)

## Abstract (arXiv)

Most consumer-grade digital cameras can only capture a limited range of luminance in real-world scenes due to sensor constraints. Besides, noise and quantization errors are often introduced in the imaging process. In order to obtain high dynamic range (HDR) images with excellent visual quality, the most common solution is to combine multiple images with different exposures. However, it is not always feasible to obtain multiple images of the same scene and most HDR reconstruction methods ignore the noise and quantization loss. In this work, we propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization. The network consists of a UNet-style base network to make full use of the hierarchical multi-scale information, a condition network to perform pattern-specific modulation and a weighting network for selectively retaining information. Moreover, we propose a Tanh_L1 loss function to balance the impact of over-exposed values and well-exposed values on the network learning. Our method achieves the state-of-the-art performance in quantitative comparisons and visual quality. The proposed HDRUNet model won the second place in the single frame track of NITRE2021 High Dynamic Range Challenge.