technical paper

AAAI 2024

February 25, 2024

Vancouver , Canada

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

keywords:

and navigation

vision for robotics & autonomous driving

3d computer vision

mapping

localization

Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view with dynamic objects, environmental noise, or other perturbations. 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 partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features and position embeddings for point clouds. We incorporate position embeddings into a Transformer module based on a neural ordinary differential equation (ODE) to efficiently represent patches within points. We employ the multi-level correspondence derived from the high feature similarity scores to facilitate alignment between point clouds. Subsequently, we use registration methods such as SVD-based algorithms to predict the transformation using corresponding point pairs. We evaluate PosDiffNet on several 3D point cloud datasets, verifying that it achieves state-of-the-art (SOTA) performance for point cloud registration in large fields of view with perturbations. The implementation code of experiments is available at https://github.com/AI-IT-AVs/PosDiffNet.

Downloads

SlidesPaperTranscript English (automatic)

Next from AAAI 2024

Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
technical paper

Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning

AAAI 2024

+5Yanqi Ge
Yanqi Ge and 7 other authors

25 February 2024

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved