SP2T adds a sparse proxy attention stream to a point transformer, improving 3D segmentation and detection accuracy on indoor and outdoor benchmarks over PTv3.
nuscenes: A multi- modal dataset for autonomous driving
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer
SP2T adds a sparse proxy attention stream to a point transformer, improving 3D segmentation and detection accuracy on indoor and outdoor benchmarks over PTv3.