An unsupervised monocular road segmentation method generates initial labels from horizon and quadrilateral geometric priors then refines them via temporal feature tracking and mutual information to reach 0.86 IoU on Cityscapes.
Expand-and-quantize: unsupervised semantic seg- 6 mentation using high-dimensional space and product quan- tization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised Monocular Road Segmentation for Autonomous Driving via Scene Geometry
An unsupervised monocular road segmentation method generates initial labels from horizon and quadrilateral geometric priors then refines them via temporal feature tracking and mutual information to reach 0.86 IoU on Cityscapes.