用多样边缘图增强遥感图像布局生成，让物体位置更精准
RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance
- 通过图像生成扩充训练样本的边缘信息，提升多样性
- 在DOTA数据集上使检测指标提升9.8/12.0（mAP50/mAP50-95）
- 适合需要精细控制遥感图像生成的科研与工程人员
扩散模型显著缓解了遥感领域标注数据稀缺的问题。尽管近期方法已实现多样且可控的布局到图像（L2I）合成，但仍存在细粒度控制不足、无法严格遵循边界框约束的问题。为此，我们提出RSGen——一个即插即用框架，利用多样边缘引导增强布局驱动的遥感图像生成。具体而言，RSGen采用渐进式增强策略：首先通过图像到图像生成，从检索的训练样本中复合丰富多样的边缘图；随后将这些边缘图作为条件输入现有L2I模型，实现边界框内的像素级控制，确保生成实例严格符合布局。在三个基线模型上的大量实验表明，RSGen显著提升了现有L2I模型的能力。例如，在DOTA数据集上使用CC-Diff进行定向目标检测时，YOLOScore的mAP50和mAP50-95分别提升+9.8/+12.0，下游检测任务的mAP提升+1.6。代码将公开：https://github.com/D-Robotics-AI-Lab/RSGen
原文摘要 · Abstract (English)
Diffusion models have significantly mitigated the impact of annotated data scarcity in remote sensing (RS). Although recent approaches have successfully harnessed these models to enable diverse and controllable Layout-to-Image (L2I) synthesis, they still suffer from limited fine-grained control and fail to strictly adhere to bounding box constraints. To address these limitations, we propose RSGen, a plug-and-play framework that leverages diverse edge guidance to enhance layout-driven RS image generation. Specifically, RSGen employs a progressive enhancement strategy: 1) it first enriches the diversity of edge maps composited from retrieved training instances via Image-to-Image generation; and 2) subsequently utilizes these diverse edge maps as conditioning for existing L2I models to enforce pixel-level control within bounding boxes, ensuring the generated instances strictly adhere to the layout. Extensive experiments across three baseline models demonstrate that RSGen significantly boosts the capabilities of existing L2I models. For instance, with CC-Diff on the DOTA dataset for oriented object detection, we achieve remarkable gains of +9.8/+12.0 in YOLOScore mAP50/mAP50-95 and +1.6 in mAP on the downstream detection task. Our code will be publicly available: https://github.com/D-Robotics-AI-Lab/RSGen
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。