Wildfire-Diff: A Controllable Diffusion Framework for Synchronized Generation of Remote Sensing Wildfire Images and Masks

遥感 计算机科学 样品(材料) 环境科学 深度学习 钥匙(锁) 随机性 失真(音乐) 一般化 变更检测 人工智能 培训(气象学) 扩散 遥感应用 任务(项目管理) 频道(广播) 图像分辨率 计算机视觉 卷积(计算机科学) 图像(数学)
作者
Junyi Wu,L Wang,Xiaoliang Meng,Haorong Liang,Xiangyu Chen,Xiaokang Zhang,Guisong Xia
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:64: 5620712-5620712
标识
DOI:10.1109/tgrs.2026.3690189
摘要

Burned area mapping based on remote sensing images is a key task in wildfire monitoring and holds significant importance for disaster assessment. In recent years, deep learning (DL) methods have made significant progress in this task and are gradually becoming the mainstream approach. However, the issue of existing training sample scarcity severely limits the accuracy and generalization of DL-based burned area mapping methods. To address this issue, we propose a controllable diffusion model, namely Wildfire-Diff, for synchronized generation of paired wildfire images and pixel-level masks. Different from current conditional diffusion models, we strengthen the realness of generated samples by constraining the spatial distribution and background of wildfires. Specifically, we design a vegetation-constrained wildfire mask generation network that can restrict burned areas to vegetation-covered regions, thereby reducing unrealistic fire scenes (e.g. wildfire on the river). Furthermore, we develop a background-aware wildfire image generation network to reduce the randomness of generated image background and mitigate the distortion issue. Benefiting from these two frameworks, our Wildfire-Diff can generate high-quality wildfire change detection samples to promote burned area mapping. Experimental results demonstrate the superiority of our Wildfire-Diff (30.42 FID) compared to other advanced diffusion models (e.g. ControlNet). Meanwhile, in downstream burned area mapping tasks, applying wildfire samples generated by our Wildfire-Diff can significantly improve the accuracy (IoU) of four change detection models (i.e., BIT, CGNet, EfficientCD and BAMCD) by at least 20%, which further reveals its great potential to address training sample scarcity and promotes downstream applications.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
LILY发布了新的文献求助10
1秒前
2秒前
香蕉觅云的应助被虚心楼房采纳,获得10
3秒前
5秒前
共享精神的应助被牧百川采纳,获得10
6秒前
彭于晏的应助被277采纳,获得10
6秒前
6秒前
7秒前
欣慰忆山完成签到,获得积分10
7秒前
情怀的应助被Hyphen采纳,获得10
8秒前
8秒前
英姑的应助被王震采纳,获得10
9秒前
10秒前
端庄书雁发布了新的文献求助10
10秒前
刘辉发布了新的文献求助10
10秒前
tingt完成签到,获得积分10
12秒前
夏夏夏发布了新的文献求助10
12秒前
dianhuaxue发布了新的文献求助10
12秒前
12秒前
13秒前
Ian发布了新的文献求助10
13秒前
Akim的应助被fx采纳,获得10
13秒前
风趣乐天发布了新的文献求助10
13秒前
13秒前
Lisa的应助被fx采纳,获得10
13秒前
zkylh的应助被fx采纳,获得10
13秒前
Lucas的应助被fx采纳,获得10
14秒前
香蕉觅云的应助被zzk采纳,获得10
14秒前
fwfl250发布了新的文献求助10
14秒前
蜡笔小新完成签到 ,获得积分10
15秒前
猴子的应助被明亮白山采纳,获得10
15秒前
15秒前
领导范儿的应助被傻傻的灵寒采纳,获得10
16秒前
16秒前
16秒前
16秒前
HHW发布了新的文献求助10
17秒前
wanci的应助被牧百川采纳,获得10
17秒前
良行知发布了新的文献求助10
17秒前
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183298
求助须知:如何正确求助?哪些是违规求助? 9572606
关于积分的说明 21826444
捐赠科研通 7780272
什么是DOI,文献DOI怎么找? 3433993
关于科研通互助平台的介绍 2558136
邀请新用户注册赠送积分活动 2480259