Are Pretrained Image Matchers Good Enough for SAR-Optical Satellite Registration? 文章

ArXiv CS.CV2026-08-07PAPERen作者: Isaac Corley, Alex Stoken, Gabriele Berton

详细信息

来源站点
ArXiv CS.CV
作者
Isaac Corley, Alex Stoken, Gabriele Berton
文章类型
PAPER
语言
en
发布日期
2026-08-07

摘要

arXiv:2604.10217v4 Announce Type: replace Abstract: Cross-modal optical--SAR (Synthetic Aperture Radar) registration is a bottleneck in remote-sensing disaster response. Modern image matchers are developed and benchmarked almost exclusively on natural-image domains. We evaluate twenty-four pretrained matcher configurations in a zero-shot setting, with no fine-tuning or domain adaptation on satellite or SAR data. The evaluation spans SpaceNet9 and two additional cross-modal benchmarks under a deterministic protocol that uses tiled large-image inference, robust geometric filtering, and tie-point-grounded metrics. Our results show uneven transfer: matchers with explicit cross-modal training do not uniformly outperform those without it. XoFTR (trained for visible--thermal matching) and RoMa achieve the lowest reported mean tie-point error at $3.0$ px on the labeled SpaceNet9 training scenes. RoMa achieves this result \emph{without any cross-modal training}. MatchAnything-ELoFTR ($3.