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

The proposed RMS-FlowNet is a novel end-to-end learning-based architecturefor accurate and efficient scene flow estimation which can operate on pointclouds of high density. For hierarchical scene flow estimation, the existingmethods depend on either expensive Farthest-Point-Sampling (FPS) orstructure-based scaling which decrease their ability to handle a large numberof points. Unlike these methods, we base our fully supervised architecture onRandom-Sampling (RS) for multiscale scene flow prediction. To this end, wepropose a novel flow embedding design which can predict more robust scene flowin conjunction with RS. Exhibiting high accuracy, our RMS-FlowNet provides afaster prediction than state-of-the-art methods and works efficiently onconsecutive dense point clouds of more than 250K points at once. Ourcomprehensive experiments verify the accuracy of RMS-FlowNet on the establishedFlyingThings3D data set with different point cloud densities and validate ourdesign choices. Additionally, we show that our model presents a competitiveability to generalize towards the real-world scenes of KITTI data set withoutfine-tuning.

RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds