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

End-to-end deep-learning networks recently demonstrated extremely goodperfor- mance for stereo matching. However, existing networks are difficult touse for practical applications since (1) they are memory-hungry and unable toprocess even modest-size images, (2) they have to be trained for a givendisparity range. The Practical Deep Stereo (PDS) network that we proposeaddresses both issues: First, its architecture relies on novel bottleneckmodules that drastically reduce the memory footprint in inference, andadditional design choices allow to handle greater image size during training.This results in a model that leverages large image context to resolve matchingambiguities. Second, a novel sub-pixel cross- entropy loss combined with a MAPestimator make this network less sensitive to ambiguous matches, and applicableto any disparity range without re-training. We compare PDS to state-of-the-artmethods published over the recent months, and demonstrate its superiorperformance on FlyingThings3D and KITTI sets.

Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching