# Lucky High Dynamic Range Smartphone Imaging

arXiv: https://arxiv.org/abs/2604.19976 · HTML: https://mlsanity.com/paper/2604.19976/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 64 references that are in the map.
- First posted on arXiv 21 Apr 2026.

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

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [Deep Optics for Single-shot High-dynamic-range Imaging](https://mlsanity.com/paper/1908.00620/) (2019)
- [Handheld Mobile Photography in Very Low Light](https://mlsanity.com/paper/1910.11336/) (2019)
- [What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?](https://mlsanity.com/paper/1801.06397/) (2018)
- [Multi-Bracket High Dynamic Range Imaging with Event Cameras](https://mlsanity.com/paper/2203.06622/) (2022)
- [RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image](https://mlsanity.com/paper/2309.02020/) (2023)
- [HDRFlow: Real-Time HDR Video Reconstruction with Large Motions](https://mlsanity.com/paper/2403.03447/) (2024)
- [SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging](https://mlsanity.com/paper/2407.16308/) (2024)
- [High Dynamic Range and Super-Resolution from Raw Image Bursts](https://mlsanity.com/paper/2207.14671/) (2022)
- [Convolutional Sparse Coding for High Dynamic Range Imaging](https://mlsanity.com/paper/1806.04942/) (2018)
- [AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm](https://mlsanity.com/paper/2506.23537/) (2025)
- [How to cheat with metrics in single-image HDR reconstruction](https://mlsanity.com/paper/2108.08713/) (2021)
- [MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding](https://mlsanity.com/paper/2112.05221/) (2021)
- [Gradient-based Camera Exposure Control for Outdoor Mobile Platforms](https://mlsanity.com/paper/1708.07338/) (2017)

## Abstract (arXiv)

While the human eye can perceive an impressive twenty stops of dynamic range, smartphone camera sensors remain limited to about twelve stops despite decades of research. A variety of high dynamic range (HDR) image capture and processing techniques have been proposed, and, in practice, they can extend the dynamic range by 3-5 stops for handheld photography. This paper proposes an approach that robustly captures dynamic range using a handheld smartphone camera and lightweight networks suitable for running on mobile devices. Our method operates indirectly on linear raw pixels in bracketed exposures. Every pixel in the final HDR image is a convex combination of input pixels in the neighborhood, adjusted for exposure, and thus avoids hallucination artifacts typical of recent deep image synthesis networks. We validate our system on both synthetic imagery and unseen real bracketed images -- we confirm zero-shot generalization of the method to smartphone camera captures. Our iterative inference architecture is capable of processing an arbitrary number of bracketed input photos, and we show examples from capture stacks containing 3--9 images. Our training process relies only on synthetic captures yet generalizes to unseen real photos from several cameras. Moreover, we show that this training scheme improves other SOTA methods over their pretrained counterparts.