FastMap uses fused first-order gradient kernels in a point-free global SfM pipeline to run up to 10x faster than COLMAP and GLOMAP on dense photo sets, with comparable accuracy at relaxed thresholds but weaker strict-metric precision.
A mini- mal solution for two-view focal-length estimation using two affine correspondences
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
-
FastMap: Revisiting Structure from Motion through First-Order Optimization
FastMap uses fused first-order gradient kernels in a point-free global SfM pipeline to run up to 10x faster than COLMAP and GLOMAP on dense photo sets, with comparable accuracy at relaxed thresholds but weaker strict-metric precision.