提升遥感图像生成中物体的细节保真度，让生成图像更真实可用。
Object Fidelity Diffusion for Remote Sensing Image Generation
- 基于布局提取物体先验形状，指导扩散过程生成高保真图像。
- 无需真实图像采样，生成图像在多个指标上优于现有方法。
- 特别改善小物体和多形态物体识别，适合遥感检测任务使用。
高精度可控的遥感图像生成既重要又具挑战性。现有扩散模型常因难以捕捉形态细节而生成低保真图像，影响目标检测模型的鲁棒性与可靠性。本文提出物体保真度扩散（OF-Diff），有效提升遥感图像中生成物体的保真度。首次基于布局提取物体先验形状，用于指导扩散模型；设计双分支扩散架构并引入一致性损失，在采样阶段无需真实图像即可生成高质量遥感图像；进一步引入DDPO优化扩散过程，增强生成图像多样性与语义一致性。大量实验表明，OF-Diff在关键质量指标上超越当前最优方法。尤其对多种形态及小物体类别，性能显著提升：飞机、船只、车辆的mAP分别提高8.3%、7.7%、4.0%。
原文摘要 · Abstract (English)
High-precision controllable remote sensing image generation is both meaningful and challenging. Existing diffusion models often produce low-fidelity images due to their inability to adequately capture morphological details, which may affect the robustness and reliability of object detection models. To enhance the accuracy and fidelity of generated objects in remote sensing, this paper proposes Object Fidelity Diffusion (OF-Diff), which effectively improves the fidelity of generated objects. Specifically, we are the first to extract the prior shapes of objects based on the layout for diffusion models in remote sensing. Then, we introduce a dual-branch diffusion model with diffusion consistency loss, which can generate high-fidelity remote sensing images without providing real images during the sampling phase. Furthermore, we introduce DDPO to fine-tune the diffusion process, making the generated remote sensing images more diverse and semantically consistent. Comprehensive experiments demonstrate that OF-Diff outperforms state-of-the-art methods in the remote sensing across key quality metrics. Notably, the performance of several polymorphic and small object classes shows significant improvement. For instance, the mAP increases by 8.3%, 7.7%, and 4.0% for airplanes, ships, and vehicles, respectively.
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。