Abstract
The scarcity of labeled satellite imagery remains a fundamental bottleneck for deep-learning (DL)-based wildfire monitoring systems. This paper investigates whether a diffusion-based foundation model for Earth Observation (EO), EarthSynth, can synthesize realistic post-wildfire Sentinel-2 RGB imagery conditioned on existing burn masks, without task-specific retraining. Using burn masks derived from the CalFireSeg-50 dataset (Martin et al., 2025), we design and evaluate six controlled experimental configurations that systematically vary: (i) pipeline architecture (mask-only full generation vs. inpainting with pre-fire context), (ii) prompt engineering strategy (three hand-crafted prompts and a VLM-generated prompt via Qwen2-VL), and (iii) a region-wise color-matching post-processing step. Quantitative assessment on 10 stratified test samples uses four complementary metrics: Burn IoU, burn-region color distance ({\Delta}C_burn), Darkness Contrast, and Spectral Plausibility. Results show that inpainting-based pipelines consistently outperform full-tile generation across all metrics, with the structured inpainting prompt achieving the best spatial alignment (Burn IoU = 0.456) and burn saliency (Darkness Contrast = 20.44), while color matching produces the lowest color distance ({\Delta}C_burn = 63.22) at the cost of reduced burn saliency. VLM-assisted inpainting is competitive with hand-crafted prompts. These findings provide a foundation for incorporating generative data augmentation into wildfire detection pipelines. Code and experiments are available at: this https URL
Abstract (translated)
标注卫星影像的稀缺性仍是基于深度学习的野火监测系统面临的根本瓶颈。本研究探讨了基于扩散的地球观测基础模型EarthSynth能否在无需任务特定再训练的情况下，依据现有燃烧掩膜合成逼真的灾后Sentinel-2 RGB影像。利用源自CalFireSeg-50数据集（Martin等，2025）的燃烧掩膜，我们设计并评估了六种受控实验配置，系统性地变化以下三个维度：(i) 流水线架构（仅掩膜全图生成 vs. 结合灾前背景的修复生成），(ii) 提示词工程策略（三种人工设计提示词及通过Qwen2-VL生成的视觉语言模型提示词），(iii) 基于区域的颜色匹配后处理步骤。对10个分层测试样本的定量评估采用了四项互补指标：燃烧区域交并比、燃烧区域颜色距离（{\Delta}C_burn）、暗度对比度及光谱合理性。结果表明，基于修复的流水线在所有指标上均持续优于全图生成，其中结构化修复提示词实现了最佳空间对齐（燃烧区域交并比=0.456）与燃烧显著性（暗度对比度=20.44），而颜色匹配虽产生最低颜色距离（{\Delta}C_burn=63.22），却以牺牲燃烧显著性为代价。视觉语言模型辅助的修复表现与人工设计提示词相当。这些发现为将生成式数据增强纳入野火检测流水线奠定了基础。代码与实验可访问：此https链接
URL
https://arxiv.org/abs/2604.02479
