Evidence Alignment and Transfer Boundaries in Road-Scene Geometry

Abstract

A central challenge in road-scene geometry is to compare studies whose mechanisms and validation settings do not share a single denominator. The present review uses attention-based fusion of LiDAR and camera cues for curb detection and a wavelet-transform state-space decoder for zero-shot depth estimation as focal cases for a boundary-aware synthesis. Two target papers are triangulated against 12 locally validated publications. The comparison follows sensor fusion, depth priors, attention efficiency, domain transfer, road safety and deliberately separates mechanistic interpretation from performance ranking, because the latter can conceal incompatible experimental or operational conditions. Across the evidence base, the decisive issue is alignment: sensor fusion shapes what is observed, depth priors shapes how it is compared, and road safety governs whether the conclusion can be transferred. Uncertainty is most informative when reported as part of the result rather than treated as a postscript. The contribution is a decision-oriented synthesis that connects method selection to failure cost and treats reproducibility, provenance, and bounded generalization as first-order design requirements.