LanePerf estimates lane-detection F1 on unlabeled target domains by fusing CLIP image features with lane features, achieving MAE 0.117 and Spearman's rho 0.727 on OpenLane.
Clrnet: Cross layer refinement network for lane detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LanePerf: a Performance Estimation Framework for Lane Detection
LanePerf estimates lane-detection F1 on unlabeled target domains by fusing CLIP image features with lane features, achieving MAE 0.117 and Spearman's rho 0.727 on OpenLane.