AI Paper Atlas

Research map / 3D vision / 3D generation

Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization

Aysim Toker, Qunjie Zhou, Maxim Maximov, Laura Leal-Taixe

CVPR 2021 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 171 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
jointly train satellite-to-street synthesis and retrieval (ablation)Ours · CVUSAR@1: 88.06 -> 92.56Improved
add the conditional GAN loss and discriminator (ablation)Ours · CVUSAR@1: 91.92 -> 92.56Improved
use generator bottleneck features rather than generated images for retrieval (ablation)Ours · CVUSAR@1: 89.98 -> 92.56Improved
add the retrieval head to joint training (ablation)Ours · CVUSASSIM: 0.4392 -> 0.4472Improved
add the retrieval head to joint training (ablation)Ours · CVUSAPSNR: 13.6858 -> 13.8952Improved
replace polar-transformed satellite images with the learned generator (ablation)Ours · CVUSASSIM: 0.2892 -> 0.4472Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy