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

Point cloud registration is a crucial technique in 3D computer vision with awide range of applications. However, this task can be challenging, particularlyin large fields of view with dynamic objects, environmental noise, or otherperturbations. To address this challenge, we propose a model called PosDiffNet.Our approach performs hierarchical registration based on window-level,patch-level, and point-level correspondence. We leverage a graph neural partialdifferential equation (PDE) based on Beltrami flow to obtain high-dimensionalfeatures and position embeddings for point clouds. We incorporate positionembeddings into a Transformer module based on a neural ordinary differentialequation (ODE) to efficiently represent patches within points. We employ themulti-level correspondence derived from the high feature similarity scores tofacilitate alignment between point clouds. Subsequently, we use registrationmethods such as SVD-based algorithms to predict the transformation usingcorresponding point pairs. We evaluate PosDiffNet on several 3D point clouddatasets, verifying that it achieves state-of-the-art (SOTA) performance forpoint cloud registration in large fields of view with perturbations. Theimplementation code of experiments is available athttps://github.com/AI-IT-AVs/PosDiffNet.

PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations