Seeing the Unseen in Low-light Spike Streams

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Liwen, Li, Yang, Liu, Mianzhi, Guo, Yijia, Xie, Shenghao, Ding, Ziluo, Huang, Tiejun, Ma, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914155525570560
author Hu, Liwen
Li, Yang
Liu, Mianzhi
Guo, Yijia
Xie, Shenghao
Ding, Ziluo
Huang, Tiejun
Ma, Lei
author_facet Hu, Liwen
Li, Yang
Liu, Mianzhi
Guo, Yijia
Xie, Shenghao
Ding, Ziluo
Huang, Tiejun
Ma, Lei
contents Spike camera, a type of neuromorphic sensor with high-temporal resolution, shows great promise for high-speed visual tasks. Unlike traditional cameras, spike camera continuously accumulates photons and fires asynchronous spike streams. Due to unique data modality, spike streams require reconstruction methods to become perceptible to the human eye. However, lots of methods struggle to handle spike streams in low-light high-speed scenarios due to severe noise and sparse information. In this work, we propose Diff-SPK, a diffusion-based reconstruction method. Diff-SPK effectively leverages generative priors to supplement texture information under diverse low-light conditions. Specifically, it first employs an Enhanced Texture from Inter-spike Interval (ETFI) to aggregate sparse information from low-light spike streams. Then, the encoded ETFI by a suitable encoder serve as the input of ControlNet for high-speed scenes generation. To improve the quality of results, we introduce an ETFI-based feature fusion module during the generation process.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23304
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing the Unseen in Low-light Spike Streams
Hu, Liwen
Li, Yang
Liu, Mianzhi
Guo, Yijia
Xie, Shenghao
Ding, Ziluo
Huang, Tiejun
Ma, Lei
Computer Vision and Pattern Recognition
Spike camera, a type of neuromorphic sensor with high-temporal resolution, shows great promise for high-speed visual tasks. Unlike traditional cameras, spike camera continuously accumulates photons and fires asynchronous spike streams. Due to unique data modality, spike streams require reconstruction methods to become perceptible to the human eye. However, lots of methods struggle to handle spike streams in low-light high-speed scenarios due to severe noise and sparse information. In this work, we propose Diff-SPK, a diffusion-based reconstruction method. Diff-SPK effectively leverages generative priors to supplement texture information under diverse low-light conditions. Specifically, it first employs an Enhanced Texture from Inter-spike Interval (ETFI) to aggregate sparse information from low-light spike streams. Then, the encoded ETFI by a suitable encoder serve as the input of ControlNet for high-speed scenes generation. To improve the quality of results, we introduce an ETFI-based feature fusion module during the generation process.
title Seeing the Unseen in Low-light Spike Streams
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23304