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

Efficient real-time disparity estimation is critical for the application ofstereo vision systems in various areas. Recently, stereo network based oncoarse-to-fine method has largely relieved the memory constraints and speedlimitations of large-scale network models. Nevertheless, all of the previouscoarse-to-fine designs employ constant offsets and three or more stages toprogressively refine the coarse disparity map, still resulting inunsatisfactory computation accuracy and inference time when deployed on mobiledevices. This paper claims that the coarse matching errors can be correctedefficiently with fewer stages as long as more accurate disparity candidates canbe provided. Therefore, we propose a dynamic offset prediction module to meetdifferent correction requirements of diverse objects and design an efficienttwo-stage framework. Besides, we propose a disparity-independent convolution tofurther improve the performance since it is more consistent with the localstatistical characteristics of the compact cost volume. The evaluation resultson multiple datasets and platforms clearly demonstrate that, the proposednetwork outperforms the state-of-the-art lightweight models especially formobile devices in terms of accuracy and speed. Code will be made available.

ADCPNet: Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching