# Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging

arXiv: https://arxiv.org/abs/2601.12526 · HTML: https://mlsanity.com/paper/2601.12526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Builds on (most cited first, 18 of 18)

- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Equivariant Imaging: Learning Beyond the Range Space](https://mlsanity.com/paper/2103.14756/) (2021)
- [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)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content](https://mlsanity.com/paper/2304.13625/) (2023)
- [Imaging with Equivariant Deep Learning](https://mlsanity.com/paper/2209.01725/) (2022)
- [On Unlimited Sampling and Reconstruction](https://mlsanity.com/paper/1905.03901/) (2019)
- [Unlimited Sampling from Theory to Practice: Fourier-Prony Recovery and Prototype ADC](https://mlsanity.com/paper/2105.05818/) (2021)
- [Photon Limited Non-Blind Deblurring Using Algorithm Unrolling](https://mlsanity.com/paper/2110.15314/) (2021)
- [MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding](https://mlsanity.com/paper/2112.05221/) (2021)
- [NamedCurves: Learned Image Enhancement via Color Naming](https://mlsanity.com/paper/2407.09892/) (2024)
- [JR2net: A Joint Non-Linear Representation and Recovery Network for Compressive Spectral Imaging](https://mlsanity.com/paper/2205.07770/) (2022)
- [Robust Multi-Image HDR Reconstruction for the Modulo Camera](https://mlsanity.com/paper/1707.01317/) (2017)
- [HDRTransDC: High Dynamic Range Image Reconstruction with Transformer Deformation Convolution](https://mlsanity.com/paper/2403.06831/) (2024)
- [Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications](https://mlsanity.com/paper/2504.04228/) (2025)

## Abstract (arXiv)

Modulo-Imaging (MI) offers a promising alternative for expanding the dynamic range of images by resetting the signal intensity when it reaches the saturation level. Subsequently, high-dynamic range (HDR) modulo imaging requires a recovery process to obtain the HDR image. MI is a non-convex and ill-posed problem where recent recovery networks suffer in high-noise scenarios. In this work, we formulate the HDR reconstruction task as an optimization problem that incorporates a deep prior and subsequently unrolls it into an optimization-inspired deep neural network. The network employs a lightweight convolutional denoiser for fast inference with minimal computational overhead, effectively recovering intensity values while mitigating noise. Moreover, we introduce the Scaling Equivariance term that facilitates self-supervised fine-tuning, thereby enabling the model to adapt to new modulo images that fall outside the original training distribution. Extensive evaluations demonstrate the superiority of our method compared to state-of-the-art recovery algorithms in terms of performance and quality.