P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

TL;DR

This paper introduces P2-Net, a dual framework that jointly describes and detects local features for pixel and point matching, enabling accurate cross-modal correspondences between 2D images and 3D point clouds.

Contribution

It proposes a shared latent space for 2D and 3D features, along with an ultra-wide reception mechanism and novel loss function for improved matching.

Findings

Achieves state-of-the-art indoor visual localization results.

Demonstrates competitive performance in fine-grained image and point cloud matching.

Validates effectiveness through extensive experiments.

Abstract

Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds. Despite a plethora of learning-based 2D or 3D local feature descriptors and detectors having been proposed, the derivation of a shared descriptor and joint keypoint detector that directly matches pixels and points remains under-explored by the community. This work takes the initiative to establish fine-grained correspondences between 2D images and 3D point clouds. In order to directly match pixels and points, a dual fully convolutional framework is presented that maps 2D and 3D inputs into a shared latent representation space to simultaneously describe and detect keypoints. Furthermore, an ultra-wide reception mechanism in combination with a novel loss function are designed to mitigate the intrinsic information variations between pixel and point local regions. Extensive experimental results demonstrate that our framework shows competitive performance in fine-grained matching between images and point clouds and achieves state-of-the-art results for the task of indoor visual localization. Our source code will be available at [no-name-for-blind-review].