arrow
Return

An event-oriented diffusion-refinement method for sparse events completion

delete2024-03-21
delete1
delete
OA
AI
B
Bo Zhang
韩雨琪 cover
韩雨琪 (Yuqi Han)
索
索津莉 (Jinli Suo) *
戴
戴琼海 (Qionghai Dai)
DOI:10.1038/s41598-024-57333-2delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
Event cameras or dynamic vision sensors (DVS) record asynchronous response to brightness changes instead of conventional intensity frames, and feature ultra-high sensitivity at low bandwidth. The new mechanism demonstrates great advantages in challenging scenarios with fast motion and large dynamic range. However, the recorded events might be highly sparse due to either limited hardware bandwidth or extreme photon starvation in harsh environments. To unlock the full potential of event cameras, we propose an inventive event sequence completion approach conforming to the unique characteristics of event data in both the processing stage and the output form. Specifically, we treat event streams as 3D event clouds in the spatiotemporal domain, develop a diffusion-based generative model to generate dense clouds in a coarse-to-fine manner, and recover exact timestamps to maintain the temporal resolution of raw data successfully. To validate the effectiveness of our method comprehensively, we perform extensive experiments on three widely used public datasets with different spatial resolutions, and additionally collect a novel event dataset covering diverse scenarios with highly dynamic motions and under harsh illumination. Besides generating high-quality dense events, our method can benefit downstream applications such as object classification and intensity frame reconstruction.
Keywords:
DIRECT ORAL ANTICOAGULANTS
APIXABAN
TIME
DABIGATRAN

Journal

Scientific Reports cover
Scientific Reports
IF:
3.9
Papers:
28.4W
Citations:
108.9W

Organization

Tsinghua University cover
Tsinghua University
Scholars:
1.1W
Papers: 3.9K
Citations: 9.9W
Cited Papers

Cited Papers

errShare
errSave
Chronic thromboembolic pulmonary hypertension: From transplantation to distal pulmonary endarterectomy
err2016-06-01
err0
PREAI
errAndrea M. D’Armini; Marco Morsolini; Gabriella Mattiucci; Valentina Grazioli; Maurizio Pin; Antonio Sciortino; Eloisa Arbustini; Claudio Goggi; Mario Viganò
errShare
errSave
The event-camera dataset and simulator: Event-based data for pose estimation, visual odometry, and SLAM
err2017-02-17
err379
errOAAI
errMueggler, Elias; Rebecq, Henri; Gallego, Guillermo; Delbruck, Tobi; Scaramuzza, Davide
errShare
errSave
Inhibition of glyoxalase I by S-substituted glutathiones
err2002-05-01
err0
PREAI
errRobert Vince; Susan Daluge; Wallace B. Wadd
errShare
errSave
researcher View more