HSCM-Lane improves lane segmentation with multi-level context modeling
A ResNet-based model using multi-level shifted-window context improved lane-segmentation metrics on BDD100K and transferred to TuSimple without target-domain fine-tuning.
A ResNet-based model using multi-level shifted-window context improved lane-segmentation metrics on BDD100K and transferred to TuSimple without target-domain fine-tuning.
GraphLane combined three-frame context, uncertainty-weighted graph reasoning and road-geometry constraints to improve lane-coordinate estimates in a CULane study, although its ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine