Co-Win proposes a window-attention BEV architecture for joint LiDAR vehicle detection and instance segmentation, but the claimed state-of-the-art performance is presented without any experimental data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Co-Win: Joint Object Detection and Instance Segmentation in LiDAR Point Clouds via Collaborative Window Processing
Co-Win proposes a window-attention BEV architecture for joint LiDAR vehicle detection and instance segmentation, but the claimed state-of-the-art performance is presented without any experimental data.