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

We present a novel deep neural network architecture for end-to-end scene flowestimation that directly operates on large-scale 3D point clouds. Inspired byBilateral Convolutional Layers (BCL), we propose novel DownBCL, UpBCL, andCorrBCL operations that restore structural information from unstructured pointclouds, and fuse information from two consecutive point clouds. Operating ondiscrete and sparse permutohedral lattice points, our architectural design isparsimonious in computational cost. Our model can efficiently process a pair ofpoint cloud frames at once with a maximum of 86K points per frame. Our approachachieves state-of-the-art performance on the FlyingThings3D and KITTI SceneFlow 2015 datasets. Moreover, trained on synthetic data, our approach showsgreat generalization ability on real-world data and on different pointdensities without fine-tuning.

HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds