用几何先验指导扩散模型，让雷达图像生成更准确可控。
GeoDiff-SAR: A Geometric Prior Guided Diffusion Model for SAR Image Generation
- 用轻量级多路径光线追踪构建3D几何先验，融合文本条件生成
- 在4类飞机数据上SSIM达0.812，方位一致性0.940，显著优于基线
- 适合需要精确视角控制的SAR图像生成任务，非高保真电磁重建
合成孔径雷达（SAR）图像生成可缓解数据稀缺问题，但在稀疏观测角度下的可控生成仍具挑战。现有研究提升纹理真实感，但显式几何控制能力有限。本文聚焦中间方位角补全任务：利用3D模型生成的几何先验引导扩散模型，合成稀疏角度训练数据缺失的视角。GeoDiff-SAR构建轻量级多反弹光线追踪先验，编码点云并融合文本条件，通过低秩适配改进Stable Diffusion 3.5 Medium。在真实四类飞机数据集上，其SSIM达0.812，方位一致性0.940，优于文本条件基线（0.738和0.782）。同协议下五类MSTAR车辆数据的SSIM为0.878，方位一致性0.917。结果表明，轻量3D几何先验能有效提升视角一致性，适用于可控生成，而非高保真电磁重建。
原文摘要 · Abstract (English)
Synthetic aperture radar (SAR) image generation can mitigate data scarcity, but controllablegeneration under sparse observation angles remains difficult. Recent SAR generative studies im-prove texture realism, yet explicit geometry-aware control is still limited. This paper studiesthe focused and verifiable setting of intermediate-azimuth completion: 3D-model-derived geo-metric priors guide a diffusion model to synthesize the views missing from sparse-angle trainingdata. GeoDiff-SAR constructs a lightweight multi-bounce ray-tracing prior, encodes the result-ing point cloud, and fuses it with text conditioning while adapting Stable Diffusion 3.5 Mediumthrough low-rank adaptation. On a real four-category aircraft dataset, GeoDiff-SAR reaches anSSIM of 0.812 and azimuth consistency of 0.940, compared with 0.738 and 0.782 for the text-conditioned SD3.5 Medium baseline. The same sparse-angle protocol on five MSTAR vehicleclasses yields an SSIM of 0.878 and azimuth consistency of 0.917. These results support theconclusion that a lightweight 3D geometric prior improves viewpoint adherence for controllableSAR generation; it is intended as generation guidance rather than high-fidelity electromagneticreconstruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。