用3D几何先验引导扩散模型，实现稀疏视角下可控的SAR图像生成。
PriSAR: 3D Geometric-Prior-Guided Diffusion for Parameter-Controlled SAR Image Generation
- 引入轻量级3D射线追踪先验，融合点云与文本条件控制生成
- 在4类飞机和5类车辆数据集上分别达到0.812/0.878的SSIM和0.940/0.917的方位一致性
- 适合需要可控、高视角一致性的SAR图像生成任务
合成孔径雷达（SAR）图像生成可缓解数据稀缺问题，但稀疏观测角度下的可控生成仍具挑战。现有研究虽提升了纹理真实感，但显式的几何感知控制仍有限。本文聚焦中等俯仰角补全任务：利用3D模型生成的几何先验，指导扩散模型填补稀疏角度训练数据中的缺失视角。GeoDiff-SAR构建轻量级多路径射线追踪先验，编码生成点云，并将其与文本条件融合，通过低秩适配调整Stable Diffusion 3.5 Medium模型。在真实四类飞机数据集上，该方法取得0.812的SSIM和0.940的方位一致性，优于基线模型的0.738和0.782；在五类MSTAR车辆数据集上，分别达0.878和0.917。结果表明，轻量级3D几何先验能有效提升可控SAR生成的视角一致性，其定位为生成引导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。