Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing

Paper recorded by Signals 4 on 2026-08-28 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.CV · 计算机视觉 · first seen 2026-08-31

Abstract

Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods jointly learn the target prior and cross-modal dependence from scarce paired data, overlooking a key asymmetry: only the latter intrinsically requires cross-modal correspondence. We formalize this distinction through conditional-score and denoising-r

Read on arXiv →