MinkLoc3D: Point Cloud Based Large-Scale Place Recognition
| Autor: | Jacek Komorowski |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Point cloud Computer Science - Computer Vision and Pattern Recognition Location awareness 020207 software engineering 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Discriminative model Convolutional code 0202 electrical engineering electronic engineering information engineering Code (cryptography) Graph (abstract data type) Data mining Artificial intelligence Scale (map) Representation (mathematics) business computer 0105 earth and related environmental sciences |
| Zdroj: | WACV |
| Popis: | The paper presents a learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Existing methods, such as PointNetVLAD, are based on unordered point cloud representation. They use PointNet as the first processing step to extract local features, which are later aggregated into a global descriptor. The PointNet architecture is not well suited to capture local geometric structures. Thus, state-of-the-art methods enhance vanilla PointNet architecture by adding different mechanism to capture local contextual information, such as graph convolutional networks or using hand-crafted features. We present an alternative approach, dubbed MinkLoc3D, to compute a discriminative 3D point cloud descriptor, based on a sparse voxelized point cloud representation and sparse 3D convolutions. The proposed method has a simple and efficient architecture. Evaluation on standard benchmarks proves that MinkLoc3D outperforms current state-of-the-art. Our code is publicly available on the project website: https://github.com/jac99/MinkLoc3D Winter Conference on Applications of Computer Vision (WACV) 2021. Project web site: https://github.com/jac99/MinkLoc3D |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|