Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Monroy, Brayan, Bacca, Jorge
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914294503833600
author Monroy, Brayan
Bacca, Jorge
author_facet Monroy, Brayan
Bacca, Jorge
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12526
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging
Monroy, Brayan
Bacca, Jorge
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.12526