SEM-GAT: explainable semantic pose estimation using learned graph attention
This paper proposes a Graph Neural Network (GNN)-based method for exploiting semantics and local geometry to guide the identification of reliable pointcloud registration candidates. Semantic and morphological features of the environment serve as key reference points for registration, enabling accura...
Main Authors: | Panagiotaki, E, De Martini, D, Pramatarov, G, Gadd, M, Kunze, L |
---|---|
Formato: | Conference item |
Idioma: | English |
Publicado em: |
IEEE
2024
|
Registos relacionados
-
BoxGraph: semantic place recognition and pose estimation from 3D LiDAR
Por: Pramatarov, G, et al.
Publicado em: (2021) -
Semantic interpretation and validation of graph attention-based explanations for GNN models
Por: Panagiotaki, E, et al.
Publicado em: (2024) -
That's my point: compact object-centric LiDAR pose estimation for large-scale outdoor localisation
Por: Pramatarov, G, et al.
Publicado em: (2024) -
CollabGAT: Collaborative Perception Using Graph Attention Network
Por: Ahmed N. Ahmed, et al.
Publicado em: (2024-01-01) -
PU-GAT: Point cloud upsampling with graph attention network
Por: Xuan Deng, et al.
Publicado em: (2023-12-01)