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 offer promising properties, such as high temporal resolutionand high dynamic range. These benefits have been utilized into many machinevision tasks, especially optical flow estimation. Currently, most existingevent-based works use deep learning to estimate optical flow. However, theirnetworks have not fully exploited prior hidden states and motion flows.Additionally, their supervision strategy has not fully leveraged the geometricconstraints of event data to unlock the potential of networks. In this paper,we propose EV-MGRFlowNet, an unsupervised event-based optical flow estimationpipeline with motion-guided recurrent networks using a hybridmotion-compensation loss. First, we propose a feature-enhanced recurrentencoder network (FERE-Net) which fully utilizes prior hidden states to obtainmulti-level motion features. Then, we propose a flow-guided decoder network(FGD-Net) to integrate prior motion flows. Finally, we design a hybridmotion-compensation loss (HMC-Loss) to strengthen geometric constraints for themore accurate alignment of events. Experimental results show that our methodoutperforms the current state-of-the-art (SOTA) method on the MVSEC dataset,with an average reduction of approximately 22.71% in average endpoint error(AEE). To our knowledge, our method ranks first among unsupervisedlearning-based methods.

EV-MGRFlowNet: Motion-Guided Recurrent Network for Unsupervised Event-based Optical Flow with Hybrid Motion-Compensation Loss