# Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss

arXiv: https://arxiv.org/abs/2005.07335 · HTML: https://mlsanity.com/paper/2005.07335/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2020.

## Built on by (most cited first, 30 of 71)

- [HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization](https://mlsanity.com/paper/2105.13084/) (2021)
- [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://mlsanity.com/paper/2105.10697/) (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)
- [Multi-Bracket High Dynamic Range Imaging with Event Cameras](https://mlsanity.com/paper/2203.06622/) (2022)
- [NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results](https://mlsanity.com/paper/2106.01439/) (2021)
- [RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image](https://mlsanity.com/paper/2309.02020/) (2023)
- [MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors](https://mlsanity.com/paper/2409.15273/) (2024)
- [Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models](https://mlsanity.com/paper/2411.07126/) (2024)
- [LEDiff: Latent Exposure Diffusion for HDR Generation](https://mlsanity.com/paper/2412.14456/) (2024)
- [GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild](https://mlsanity.com/paper/2211.12352/) (2022)
- [Single-Image HDR Reconstruction by Multi-Exposure Generation](https://mlsanity.com/paper/2210.15897/) (2022)
- [Luminance Attentive Networks for HDR Image and Panorama Reconstruction](https://mlsanity.com/paper/2109.06688/) (2021)
- [High Dynamic Range and Super-Resolution from Raw Image Bursts](https://mlsanity.com/paper/2207.14671/) (2022)
- [Perceptual Image Enhancement for Smartphone Real-Time Applications](https://mlsanity.com/paper/2210.13552/) (2022)
- [Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising](https://mlsanity.com/paper/2405.14304/) (2024)
- [Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction](https://mlsanity.com/paper/2304.12372/) (2023)
- [Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field](https://mlsanity.com/paper/2406.07329/) (2024)
- [GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR](https://mlsanity.com/paper/2504.10809/) (2025)
- [How to cheat with metrics in single-image HDR reconstruction](https://mlsanity.com/paper/2108.08713/) (2021)
- [Casual Indoor HDR Radiance Capture from Omnidirectional Images](https://mlsanity.com/paper/2208.07903/) (2022)
- [Learning a Practical SDR-to-HDRTV Up-conversion using New Dataset and Degradation Models](https://mlsanity.com/paper/2303.13031/) (2023)
- [Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction](https://mlsanity.com/paper/2309.03900/) (2023)
- [Intrinsic Single-Image HDR Reconstruction](https://mlsanity.com/paper/2409.13803/) (2024)
- [MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding](https://mlsanity.com/paper/2112.05221/) (2021)
- [HDR Imaging with Spatially Varying Signal-to-Noise Ratios](https://mlsanity.com/paper/2303.17253/) (2023)
- [AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results](https://mlsanity.com/paper/2508.13479/) (2025)
- [HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN](https://mlsanity.com/paper/2110.01660/) (2021)
- [Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images](https://mlsanity.com/paper/2312.15942/) (2023)
- [Semantic Aware Diffusion Inverse Tone Mapping](https://mlsanity.com/paper/2405.15468/) (2024)

## Abstract (arXiv)

Digital cameras can only capture a limited range of real-world scenes' luminance, producing images with saturated pixels. Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of luminance, but are not able to hallucinate plausible textures, producing results with artifacts in the saturated areas. In this paper, we present a novel learning-based approach to reconstruct an HDR image by recovering the saturated pixels of an input LDR image in a visually pleasing way. Previous deep learning-based methods apply the same convolutional filters on well-exposed and saturated pixels, creating ambiguity during training and leading to checkerboard and halo artifacts. To overcome this problem, we propose a feature masking mechanism that reduces the contribution of the features from the saturated areas. Moreover, we adapt the VGG-based perceptual loss function to our application to be able to synthesize visually pleasing textures. Since the number of HDR images for training is limited, we propose to train our system in two stages. Specifically, we first train our system on a large number of images for image inpainting task and then fine-tune it on HDR reconstruction. Since most of the HDR examples contain smooth regions that are simple to reconstruct, we propose a sampling strategy to select challenging training patches during the HDR fine-tuning stage. We demonstrate through experimental results that our approach can reconstruct visually pleasing HDR results, better than the current state of the art on a wide range of scenes.