English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Event cameras are novel vision sensors that sample, in an asynchronousfashion, brightness increments with low latency and high temporal resolution.The resulting streams of events are of high value by themselves, especially forhigh speed motion estimation. However, a growing body of work has also focusedon the reconstruction of intensity frames from the events, as this allowsbridging the gap with the existing literature on appearance- and frame-basedcomputer vision. Recent work has mostly approached this problem using neuralnetworks trained with synthetic, ground-truth data. In this work we approach,for the first time, the intensity reconstruction problem from a self-supervisedlearning perspective. Our method, which leverages the knowledge of the innerworkings of event cameras, combines estimated optical flow and the event-basedphotometric constancy to train neural networks without the need for anyground-truth or synthetic data. Results across multiple datasets show that theperformance of the proposed self-supervised approach is in line with thestate-of-the-art. Additionally, we propose a novel, lightweight neural networkfor optical flow estimation that achieves high speed inference with only aminor drop in performance.

Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy