.png){kind=icon}
返回
DiffVector: Boosting Diffusion Framework for Building Vector Extraction From Remote Sensing Images
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3528474.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Building vector maps play an essential role in many remote sensing (RS) applications, thereby boosting the deep learning (DL)-based automatic building vector extraction methods. These approaches have achieved pleasant overall accuracy, but their predict-style framework struggles with perceiving subtle details within a tiny area, such as corners and adjacent walls. In this study, we introduce a denoising diffusion framework called DiffVector to generate representations for direct building vector extraction from the RS images. First, we develop a hierarchical diffusion transformer (HiDiT) to conditionally generate robust representations for detecting nodes and extracting corresponding features. The conditions of HiDiT are multilevel boundary attentive maps encoded from input RS images through a topology-concentrated Swin Transformer (TCSwin). Subsequently, an edge-biased graph diffusion transformer (EGDiT) takes extracted node features as conditions to produce new visual descriptors for the adjacency matrix prediction. In EGDiT, we replace the standard self-attention (SA) operation with an edge-biased attention (EBA) to inject edge information for training stabilization. Furthermore, given typical challenges of training difficulty and weak perceptive ability in convectional diffusion paradigms, we conduct an isomorphic training strategy (ITS), ensuring that the training procedures of both HiDiT and EGDiT precisely mirror the inference phase. Quantitative and qualitative experiments have evidently demonstrated that DiffVector can achieve competitive performance compared with existing modern approaches, especially in the metrics assessing topology quality.
Keyword:
Buildings
Vectors
Training
Transformers
Feature extraction
Image edge detection
Remote sensing
Image segmentation
Diffusion models
Sparse matrices
Building extraction
deep learning (DL)
diffusion model (DM)
vector extraction
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏Multiscale Location Attention Network for Building and Water Segmentation of Remote Sensing Image用于遥感影像建筑物和水体分割的多尺度位置注意网络
PREAI
分享收藏Boundary Shape-Preserving Model for Building Mapping From High-Resolution Remote Sensing Images高分辨率遥感影像建筑物映射的边界保形模型
PREAI
分享收藏SAMPolyBuild: Adapting the Segment Anything Model for polygonal building extractionSAMPolyBuild: 为多边形建筑提取调整Segment anyying模型
PREAI
分享收藏Sensorless Control of Z Source Inverter fed BLDC Motor Drive by FOC - DTC Hybrid Control Strategy Using Fuzzy Logic Controller采用模糊逻辑控制器的foc-dtc混合控制策略的Z源逆变器馈电BLDC电机驱动的无传感器控制
PREAI
分享收藏Self-focusing effects of dispositional self-consciousness, mirror presence, and audience presence.性格自我意识、镜像存在和观众存在的自我聚焦效应。
PREAI
分享收藏From local context-aware to non-local: A road extraction network via guidance of multi-spectral image从局部上下文感知到非局部: 基于多光谱图像引导的道路提取网络
PREAI
分享收藏
查看更多内容