FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusion
This work addresses the problem of limited training data for wildfire detection and monitoring models, offering a method to enhance datasets for downstream tasks, though it is incremental as it builds on existing diffusion models.
The paper tackles the scarcity of annotated wildfire images by introducing FLAME Diffuser, a training-free diffusion-based framework that generates realistic wildfire images with paired ground truth, using augmented masks and Perlin noise to improve image quality as measured by metrics like normalized Frechet Inception Distance and CLIP Score.
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.