
提案されたMinkUNeXtアーキテクチャは、従来の3D疎な畳み込みに依存することで、場所認識の最先端を超える可能性を示しています。


coremsg

minkunext-point-cloud-based-large-scale-place-recognition-using-3d-sparse-convolutions


MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions


title_rewrite


The proposed SelFLoc architecture leverages asymmetric convolutions and selective feature fusion to effectively extract and integrate discriminative features from point clouds for robust and accurate place recognition.


selective-feature-fusion-for-enhancing-point-cloud-based-place-recognition-in-large-scale-urban-environments


Selective Feature Fusion for Enhancing Point Cloud-based Place Recognition in Large-scale Urban Environments
