Moving Symbol sets, global open methods
Eric Brachmann @eric_brachmann Map-relative Pose Regression CVPR2024 highlight) For years absolute pose regression did not work. There was some success by massively synthesising scene-specific data. We train scene-agnostic APR and it works. Paper: https://arxiv.org/abs/2404.09884 Page: https://nianticlabs.github.io/marepo https://pic.twitter.com/uLNMFMQ42L Replying to @eric_brachmann There ought to be a concise moving symbol set to describe precisely this algorithm, not
Read More »