Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, Liwen, Ding, Ziluo, Liu, Mianzhi, Ma, Lei, Huang, Tiejun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913420142444544
author Hu, Liwen
Ding, Ziluo
Liu, Mianzhi
Ma, Lei
Huang, Tiejun
author_facet Hu, Liwen
Ding, Ziluo
Liu, Mianzhi
Ma, Lei
Huang, Tiejun
contents As a neuromorphic sensor with high temporal resolution, spike camera can generate continuous binary spike streams to capture per-pixel light intensity. We can use reconstruction methods to restore scene details in high-speed scenarios. However, due to limited information in spike streams, low-light scenes are difficult to effectively reconstruct. In this paper, we propose a bidirectional recurrent-based reconstruction framework, including a Light-Robust Representation (LR-Rep) and a fusion module, to better handle such extreme conditions. LR-Rep is designed to aggregate temporal information in spike streams, and a fusion module is utilized to extract temporal features. Additionally, we have developed a reconstruction benchmark for high-speed low-light scenes. Light sources in the scenes are carefully aligned to real-world conditions. Experimental results demonstrate the superiority of our method, which also generalizes well to real spike streams. Related codes and proposed datasets will be released after publication.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10461
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams
Hu, Liwen
Ding, Ziluo
Liu, Mianzhi
Ma, Lei
Huang, Tiejun
Computer Vision and Pattern Recognition
As a neuromorphic sensor with high temporal resolution, spike camera can generate continuous binary spike streams to capture per-pixel light intensity. We can use reconstruction methods to restore scene details in high-speed scenarios. However, due to limited information in spike streams, low-light scenes are difficult to effectively reconstruct. In this paper, we propose a bidirectional recurrent-based reconstruction framework, including a Light-Robust Representation (LR-Rep) and a fusion module, to better handle such extreme conditions. LR-Rep is designed to aggregate temporal information in spike streams, and a fusion module is utilized to extract temporal features. Additionally, we have developed a reconstruction benchmark for high-speed low-light scenes. Light sources in the scenes are carefully aligned to real-world conditions. Experimental results demonstrate the superiority of our method, which also generalizes well to real spike streams. Related codes and proposed datasets will be released after publication.
title Learning to Robustly Reconstruct Low-light Dynamic Scenes from Spike Streams
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.10461