计算机科学
人工智能
计算机视觉
翻译(生物学)
图像(数学)
模式识别(心理学)
匹配(统计)
图像分割
图像处理
图像翻译
流量(数学)
图像匹配
特征提取
特征(语言学)
迭代重建
光流
图像配准
算法
作者
Jeongwon Ryu,Youngtack Oh,Minseok Seo,Byungtae Ahn,Dong‐Geol Choi
标识
DOI:10.1109/lgrs.2026.3742531
摘要
Synthetic Aperture Radar (SAR) imagery enables reliable observations regardless of weather conditions or acquisition time; however, its interpretation is challenging due to speckle noise and complex scattering characteristics that obscure spatial structures. To alleviate this limitation, SAR-to-optical image translation has been proposed to translate SAR imagery into optical-like images. Existing SAR-to-optical image translation models can struggle to preserve structural consistency, such as object layouts and spatial relationships, as they primarily optimize for distribution matching rather than structure-level fidelity. In this paper, we formulate SAR-to-optical image translation from the perspective of structural consistency, where preserving spatial correspondence between input and output is essential. We introduce a flow-based framework that learns SAR-conditioned transformations defined by ordinary differential equations (ODE), modeling translation as a trajectory that continuously deforms SAR-aligned latent representations into their optical counterparts. By explicitly tracking how each SAR structure evolves along this trajectory, the framework naturally preserves geometric layouts and spatial relationships encoded in SAR imagery. Quantitative and qualitative results on the SAR2Opt dataset demonstrate improved perceptual and distributional quality over the evaluated baselines while preserving structural information derived from the SAR input.
科研通智能强力驱动
Strongly Powered by AbleSci AI