GFSR combines LaneIoU-guided confidence calibration with adaptive gated location refinement to improve geometric quality and robustness in lane detection, reporting SOTA F1 scores on CULane and CurveLanes.
Generating dynamic kernels via transformers for lane detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GFSR: Geometric Fidelity and Spatial Refinement for Reliable Lane Detection
GFSR combines LaneIoU-guided confidence calibration with adaptive gated location refinement to improve geometric quality and robustness in lane detection, reporting SOTA F1 scores on CULane and CurveLanes.