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

Understanding the flow in 3D space of sparsely sampled points between twoconsecutive time frames is the core stone of modern geometric-driven systemssuch as VR/AR, Robotics, and Autonomous driving. The lack of real,non-simulated, labeled data for this task emphasizes the importance of self- orun-supervised deep architectures. This work presents a new self-supervisedtraining method and an architecture for the 3D scene flow estimation underocclusions. Here we show that smart multi-layer fusion between flow predictionand occlusion detection outperforms traditional architectures by a large marginfor occluded and non-occluded scenarios. We report state-of-the-art results onFlyingthings3D and KITTI datasets for both the supervised and self-supervisedtraining.

Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds