Nature

RFGLNet for adverse weather domain-generalized semantic segmentation with frequency low-rank enhancement

Semantic segmentation in adverse weather conditions presents significant challenges due to insufficient image brightness, excessive noise, and blurred object boundaries, which hinder the performance ...
Nature

Real-time semantic segmentation of driving scenes via effective attention-based information fusion and hybrid encoder

Semantic segmentation is an important computer vision task due to its multiple applications in real-world scenarios, including autonomous driving, medical image analysis, remote sensing imagery, fault ...
Donga Science

DGIST–MIT team wins global ICRA 2026 ‘robot vision’ challenge for complex outdoor environments

New AI visual perception framework combining DINOv3 and Mask2Former tops 56 teams in GOOSE 2D semantic segmentation at the ICRA 2026 field robotics workshop ...
DLR

DLR-SkyScapes: Aerial Semantic Segmentation Dataset for HD-mapping

High-Definition(HD) mapping is in many applications from autonomous driving to infrastructure monitoring, and urban management essential for the understanding of complex urban infrastructure with ...