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

In this work, we propose a method that combines unsupervised deep learningpredictions for optical flow and monocular disparity with a model basedoptimization procedure for instantaneous camera pose. Given the flow anddisparity predictions from the network, we apply a RANSAC outlier rejectionscheme to find an inlier set of flows and disparities, which we use to solvefor the relative camera pose in a least squares fashion. We show that thispipeline is fully differentiable, allowing us to combine the pose with thenetwork outputs as an additional unsupervised training loss to further refinethe predicted flows and disparities. This method not only allows us to directlyregress relative pose from the network outputs, but also automatically segmentsaway pixels that do not fit the rigid scene assumptions that many unsupervisedstructure from motion methods apply, such as on independently moving objects.We evaluate our method on the KITTI dataset, and demonstrate state of the artresults, even in the presence of challenging independently moving objects.

Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion