FLAME Diffuser：基于掩码引导扩散的野火图像合成
FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion
AI总结：
本文提出无需训练的FLAME Diffuser框架，利用真实野火掩码与Perlin噪声引导扩散生成逼真野火图像，并通过多项指标验证其质量，用于增强野火检测与监测数据集。
摘要：
野火对生态系统和人类基础设施构成重大威胁，导致广泛的破坏和环境退化。深度学习和生成模型的最新进展为野火检测与监测提供了新方法。然而，带标注的野火图像稀缺，限制了用于这些任务的鲁棒模型的开发。在本工作中，我们提出了FLAME Diffuser，一个无需训练、基于扩散的框架，旨在生成具有成对真值的逼真野火图像。我们的框架使用从真实野火数据中采样的增强掩码，并应用Perlin噪声来引导逼真火焰的生成。通过控制这些元素在图像中的放置位置，我们在保持原始图像风格的同时确保精确融合。我们使用归一化Frechet Inception Distance、CLIP Score以及自定义的CLIP Confidence指标评估生成的图像，证明了合成野火图像的高质量和逼真度。具体而言，本工作中Perlin噪声的融合显著提升了合成图像的质量。所提出的方法对于增强下游任务（如野火检测和监测）中使用的数据集尤其有价值。
英文摘要：
Wildfires are a significant threat to ecosystems and human infrastructure, leading to widespread destruction and environmental degradation. Recent advancements in deep learning and generative models have enabled new methods for wildfire detection and monitoring. However, the scarcity of annotated wildfire images limits the development of robust models for these tasks. In this work, we present the FLAME Diffuser, a training-free, diffusion-based framework designed to generate realistic wildfire images with paired ground truth. Our framework uses augmented masks, sampled from real wildfire data, and applies Perlin noise to guide the generation of realistic flames. By controlling the placement of these elements within the image, we ensure precise integration while maintaining the original images style. We evaluate the generated images using normalized Frechet Inception Distance, CLIP Score, and a custom CLIP Confidence metric, demonstrating the high quality and realism of the synthesized wildfire images. Specifically, the fusion of Perlin noise in this work significantly improved the quality of synthesized images. The proposed method is particularly valuable for enhancing datasets used in downstream tasks such as wildfire detection and monitoring.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
