Text2Loc: 3D Point Cloud Localization from Natural Language

arXiv:2311.15977v2 Announce Type: replace
Abstract: We tackle the problem of 3D point cloud localization based on a few natural linguistic descriptions and introduce a novel neural network, Text2Loc, that fully interprets the semantic relationship between points and text. Text2Loc follows a coarse-to-fine localization pipeline: text-submap global place recognition, followed by fine localization. In global place recognition, relational dynamics among each textual hint are captured in a hierarchical transformer with max-pooling (HTM), whereas a balance between positive and negative pairs is …

arxiv cloud cs.cv language localization natural natural language type