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

Existing 3D scene flow estimation methods provide the 3D geometry and 3Dmotion of a scene and gain a lot of interest, for example in the context ofautonomous driving. These methods are traditionally based on a temporal seriesof stereo images. In this paper, we propose a novel monocular 3D scene flowestimation method, called Mono-SF. Mono-SF jointly estimates the 3D structureand motion of the scene by combining multi-view geometry and single-view depthinformation. Mono-SF considers that the scene flow should be consistent interms of warping the reference image in the consecutive image based on theprinciples of multi-view geometry. For integrating single-view depth in astatistical manner, a convolutional neural network, called ProbDepthNet, isproposed. ProbDepthNet estimates pixel-wise depth distributions from a singleimage rather than single depth values. Additionally, as part of ProbDepthNet, anovel recalibration technique for regression problems is proposed to ensurewell-calibrated distributions. Our experiments show that Mono-SF outperformsstate-of-the-art monocular baselines and ablation studies support the Mono-SFapproach and ProbDepthNet design.

Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes