Metraipolis › archive › dc_27da0835ec97
Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing — arXiv:2608.28517
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28517
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:33:20.757Z
- SHA-256 of the archived text
a9bf1bae9e8d037f505870db6846317fbf274b52a41156d8cf5f64eaac8aefde- Stable URL of this page
https://metraipolis.com/documento/dc_27da0835ec97
How to cite
Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing — arXiv:2608.28517 — arXiv (en), https://arxiv.org/abs/2608.28517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27da0835ec97 (Metraipolis archive dc_27da0835ec97, sha256 a9bf1bae9e8d037f505870db6846317fbf274b52a41156d8cf5f64eaac8aefde)
BibTeX
@misc{dc27da0835ec97,
title = {Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing — arXiv:2608.28517},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28517},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27da0835ec97; sha256 a9bf1bae9e8d037f505870db6846317fbf274b52a41156d8cf5f64eaac8aefde},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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-risk analyses and propose Learning the Target Priors Before Image Translation (LTP-BIT), a prior-first paradigm that decouples the two learning tasks. LTP-BIT first learns a target-domain generative prior from large-scale unpaired imagery, then retains the pretrained backbone weights and learns source-conditioned control through P-DART, a parameter-efficient dual-stream architecture. Controlled experiments show that prior matching and scaling primarily improve target-domain realism, whereas instance fidelity relies more strongly on conditional adaptation. LTP-BIT achieves state-of-the-art performance across SAR-to-RGB and NIR-to-RGB benchmarks using only 9.81% task-specific parameters. On QXS-SAROPT, it retains near-full-data instance fidelity with only 25% of the paired samples. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28517 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T11:10:05.339Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).