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 |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IEEE
2024
|
Similar Items
-
BoxGraph: semantic place recognition and pose estimation from 3D LiDAR
by: Pramatarov, G, et al.
Published: (2021) -
Semantic interpretation and validation of graph attention-based explanations for GNN models
by: Panagiotaki, E, et al.
Published: (2024) -
That's my point: compact object-centric LiDAR pose estimation for large-scale outdoor localisation
by: Pramatarov, G, et al.
Published: (2024) -
PU-GAT: Point cloud upsampling with graph attention network
by: Xuan Deng, et al.
Published: (2023-12-01) -
omicsGAT: Graph Attention Network for Cancer Subtype Analyses
by: Sudipto Baul, et al.
Published: (2022-09-01)