# HDR Imaging with Spatially Varying Signal-to-Noise Ratios

arXiv: https://arxiv.org/abs/2303.17253 · HTML: https://mlsanity.com/paper/2303.17253/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [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)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [Deep High Dynamic Range Imaging with Large Foreground Motions](https://mlsanity.com/paper/1711.08937/) (2017)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections](https://mlsanity.com/paper/1606.08921/) (2016)
- [Quanta Burst Photography](https://mlsanity.com/paper/2006.11840/) (2020)
- [High Flux Passive Imaging with Single-Photon Sensors](https://mlsanity.com/paper/1902.10190/) (2019)
- [What Does a One-Bit Quanta Image Sensor Offer?](https://mlsanity.com/paper/2208.10350/) (2022)
- [HDR Imaging with Quanta Image Sensors: Theoretical Limits and Optimal Reconstruction](https://mlsanity.com/paper/2011.03614/) (2020)
- [HDR Denoising and Deblurring by Learning Spatio-temporal Distortion Models](https://mlsanity.com/paper/2012.12009/) (2020)
- [HDRfeat: A Feature-Rich Network for High Dynamic Range Image Reconstruction](https://mlsanity.com/paper/2211.04238/) (2022)

## Built on by (most cited first, 8 of 8)

- [Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis](https://mlsanity.com/paper/2412.02168/) (2024)
- [Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universality](https://mlsanity.com/paper/2306.17367/) (2023)
- [BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes](https://mlsanity.com/paper/2510.09996/) (2025)
- [Quanta Video Restoration](https://mlsanity.com/paper/2410.14994/) (2024)
- [Generative Photographic Control for Scene-Consistent Video Cinematic Editing](https://mlsanity.com/paper/2511.12921/) (2025)
- [Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation](https://mlsanity.com/paper/2404.10358/) (2024)
- [iHDR: Iterative HDR Imaging with Arbitrary Number of Exposures](https://mlsanity.com/paper/2505.22971/) (2025)
- [Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection](https://mlsanity.com/paper/2608.30400/) (2026)

## Abstract (arXiv)

While today's high dynamic range (HDR) image fusion algorithms are capable of blending multiple exposures, the acquisition is often controlled so that the dynamic range within one exposure is narrow. For HDR imaging in photon-limited situations, the dynamic range can be enormous and the noise within one exposure is spatially varying. Existing image denoising algorithms and HDR fusion algorithms both fail to handle this situation, leading to severe limitations in low-light HDR imaging. This paper presents two contributions. Firstly, we identify the source of the problem. We find that the issue is associated with the co-existence of (1) spatially varying signal-to-noise ratio, especially the excessive noise due to very dark regions, and (2) a wide luminance range within each exposure. We show that while the issue can be handled by a bank of denoisers, the complexity is high. Secondly, we propose a new method called the spatially varying high dynamic range (SV-HDR) fusion network to simultaneously denoise and fuse images. We introduce a new exposure-shared block within our custom-designed multi-scale transformer framework. In a variety of testing conditions, the performance of the proposed SV-HDR is better than the existing methods.