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

Recent advanced studies have spent considerable human efforts on optimizingnetwork architectures for stereo matching but hardly achieved both highaccuracy and fast inference speed. To ease the workload in network design,neural architecture search (NAS) has been applied with great success to varioussparse prediction tasks, such as image classification and object detection.However, existing NAS studies on the dense prediction task, especially stereomatching, still cannot be efficiently and effectively deployed on devices ofdifferent computing capabilities. To this end, we propose to train an elasticand accurate network for stereo matching (EASNet) that supports various 3Darchitectural settings on devices with different computing capabilities. Giventhe deployment latency constraint on the target device, we can quickly extracta sub-network from the full EASNet without additional training while theaccuracy of the sub-network can still be maintained. Extensive experiments showthat our EASNet outperforms both state-of-the-art human-designed and NAS-basedarchitectures on Scene Flow and MPI Sintel datasets in terms of model accuracyand inference speed. Particularly, deployed on an inference GPU, EASNetachieves a new SOTA 0.73 EPE on the Scene Flow dataset with 100 ms, which is4.5$\times$ faster than LEAStereo with a better quality model.

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching