SegRoadv2: a hybrid deformable self-attention and convolutional network for road extraction with connectivity structure
Sign Up to like & getrecommendations! Published in 2025 at "International Journal of Digital Earth"
DOI: 10.1080/17538947.2025.2480267
Abstract: ABSTRACT Road extraction is crucial for navigation, autonomous driving, and smart city development. With advancements in remote sensing and deep learning, the extraction of road information from remote sensing images has emerged as a prevalent… read more here.
Keywords: deformable self; structure; road; extraction ... See more keywords
Multi-Exposure Image Fusion via Deformable Self-Attention
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2023.3242824
Abstract: Most multi-exposure image fusion (MEF) methods perform unidirectional alignment within limited and local regions, which ignore the effects of augmented locations and preserve deficient global features. In this work, we propose a multi-scale bidirectional alignment… read more here.
Keywords: deformable self; self attention; image fusion; attention ... See more keywords