Abstract | ||
---|---|---|
•Proposed a Position-Aware Transformer (PAT) architecture that leverages the Adaptive Multi-Scale Position Encoding (AMSPE) to encode both global and local position information for better point feature representations.•Proposed a 3D Correlation-Guided Enhancement (CGE) network to alleviate the ambiguous or noisy representations in the 2D feature projection.•The proposed method outperforms the state-of-the-art methods in both quantitative and qualitative comparisons. |
Year | DOI | Venue |
---|---|---|
2023 | 10.1016/j.patcog.2022.109097 | Pattern Recognition |
Keywords | DocType | Volume |
Implicit 3D representation,Multi-scale 3D position encoding,3D Correlation-Guided Attentions | Journal | 134 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qing Mao | 1 | 0 | 0.34 |
Rui Li | 2 | 6 | 2.08 |
Yu Zhu | 3 | 88 | 12.65 |
Jinqiu Sun | 4 | 9 | 4.51 |
Yanning Zhang | 5 | 1613 | 176.32 |