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, offering high temporal resolutions and high dynamic ranges,have brought a new perspective to address common challenges (e.g., motion blurand low light) in monocular depth estimation. However, how to effectivelyexploit the sparse spatial information and rich temporal cues from asynchronousevents remains a challenging endeavor. To this end, we propose a novelevent-based monocular depth estimator with recurrent transformers, namelyEReFormer, which is the first pure transformer with a recursive mechanism toprocess continuous event streams. Technically, for spatial modeling, a noveltransformer-based encoder-decoder with a spatial transformer fusion module ispresented, having better global context information modeling capabilities thanCNN-based methods. For temporal modeling, we design a gate recurrent visiontransformer unit that introduces a recursive mechanism into transformers,improving temporal modeling capabilities while alleviating the expensive GPUmemory cost. The experimental results show that our EReFormer outperformsstate-of-the-art methods by a margin on both synthetic and real-world datasets.We hope that our work will attract further research to develop stunningtransformers in the event-based vision community. Our open-source code can befound in the supplemental material.

Event-based Monocular Dense Depth Estimation with Recurrent Transformers