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

Non-rigid point cloud registration is a key component in many computer visionand computer graphics applications. The high complexity of the unknownnon-rigid motion make this task a challenging problem. In this paper, we breakdown this problem via hierarchical motion decomposition. Our method calledNeural Deformation Pyramid (NDP) represents non-rigid motion using a pyramidarchitecture. Each pyramid level, denoted by a Multi-Layer Perception (MLP),takes as input a sinusoidally encoded 3D point and outputs its motionincrements from the previous level. The sinusoidal function starts with a lowinput frequency and gradually increases when the pyramid level goes down. Thisallows a multi-level rigid to nonrigid motion decomposition and also speeds upthe solving by 50 times compared to the existing MLP-based approach. Our methodachieves advanced partialto-partial non-rigid point cloud registration resultson the 4DMatch/4DLoMatch benchmark under both no-learned and supervisedsettings.

Non-rigid Point Cloud Registration with Neural Deformation Pyramid