HDR Imaging for Dynamic Scenes with Events

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiaopeng, Li, Zhaoyuan, Zeng, Cien, Fan, Chen, Zhao, Lei, Deng, Lei, Yu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916192446316544
author Xiaopeng, Li
Zhaoyuan, Zeng
Cien, Fan
Chen, Zhao
Lei, Deng
Lei, Yu
author_facet Xiaopeng, Li
Zhaoyuan, Zeng
Cien, Fan
Chen, Zhao
Lei, Deng
Lei, Yu
contents High dynamic range imaging (HDRI) for real-world dynamic scenes is challenging because moving objects may lead to hybrid degradation of low dynamic range and motion blur. Existing event-based approaches only focus on a separate task, while cascading HDRI and motion deblurring would lead to sub-optimal solutions, and unavailable ground-truth sharp HDR images aggravate the predicament. To address these challenges, we propose an Event-based HDRI framework within a Self-supervised learning paradigm, i.e., Self-EHDRI, which generalizes HDRI performance in real-world dynamic scenarios. Specifically, a self-supervised learning strategy is carried out by learning cross-domain conversions from blurry LDR images to sharp LDR images, which enables sharp HDR images to be accessible in the intermediate process even though ground-truth sharp HDR images are missing. Then, we formulate the event-based HDRI and motion deblurring model and conduct a unified network to recover the intermediate sharp HDR results, where both the high dynamic range and high temporal resolution of events are leveraged simultaneously for compensation. We construct large-scale synthetic and real-world datasets to evaluate the effectiveness of our method. Comprehensive experiments demonstrate that the proposed Self-EHDRI outperforms state-of-the-art approaches by a large margin. The codes, datasets, and results are available at https://lxp-whu.github.io/Self-EHDRI.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03210
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HDR Imaging for Dynamic Scenes with Events
Xiaopeng, Li
Zhaoyuan, Zeng
Cien, Fan
Chen, Zhao
Lei, Deng
Lei, Yu
Computer Vision and Pattern Recognition
Image and Video Processing
High dynamic range imaging (HDRI) for real-world dynamic scenes is challenging because moving objects may lead to hybrid degradation of low dynamic range and motion blur. Existing event-based approaches only focus on a separate task, while cascading HDRI and motion deblurring would lead to sub-optimal solutions, and unavailable ground-truth sharp HDR images aggravate the predicament. To address these challenges, we propose an Event-based HDRI framework within a Self-supervised learning paradigm, i.e., Self-EHDRI, which generalizes HDRI performance in real-world dynamic scenarios. Specifically, a self-supervised learning strategy is carried out by learning cross-domain conversions from blurry LDR images to sharp LDR images, which enables sharp HDR images to be accessible in the intermediate process even though ground-truth sharp HDR images are missing. Then, we formulate the event-based HDRI and motion deblurring model and conduct a unified network to recover the intermediate sharp HDR results, where both the high dynamic range and high temporal resolution of events are leveraged simultaneously for compensation. We construct large-scale synthetic and real-world datasets to evaluate the effectiveness of our method. Comprehensive experiments demonstrate that the proposed Self-EHDRI outperforms state-of-the-art approaches by a large margin. The codes, datasets, and results are available at https://lxp-whu.github.io/Self-EHDRI.
title HDR Imaging for Dynamic Scenes with Events
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2404.03210