New AI research tackles crack segmentation, satellite image synthesis, and 3D shape matching
ByPulseAugur Editorial·
Summary by gemini-2.5-flash-lite
from 10 sources
Researchers have developed UnGAP, a novel framework for real-time crack segmentation that actively uses uncertainty estimation to refine feature learning. This approach transforms aleatoric uncertainty into a visual prompt, calibrating feature distributions through pixel-wise affine transformations to improve accuracy in ambiguous regions. The method also incorporates a boundary-aware detection head for enhanced precision, balancing segmentation accuracy with real-time inference speeds.
AI
Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncertainty estimation as a passive endpoint for post-…
arXiv:2605.04557v1 Announce Type: new Abstract: High-resolution satellite images are often scarce and costly, especially for remote areas or infrequent events. This shortage hampers the development and testing of machine learning models for land-cover classification, change detec…
High-resolution satellite images are often scarce and costly, especially for remote areas or infrequent events. This shortage hampers the development and testing of machine learning models for land-cover classification, change detection, and disaster monitoring. In this paper, we…
arXiv:2605.03837v1 Announce Type: new Abstract: Recovering scene color from images captured in scattering media is a fundamental inverse problem in optical imaging. Yet the problem is intrinsically ill-posed as multiple solutions can explain the same observation, and prediction e…
Recovering scene color from images captured in scattering media is a fundamental inverse problem in optical imaging. Yet the problem is intrinsically ill-posed as multiple solutions can explain the same observation, and prediction error cannot be controlled without understanding …
arXiv:2605.02380v1 Announce Type: new Abstract: Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncert…
arXiv:2303.10971v2 Announce Type: replace Abstract: The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds. While point clouds are a common representation of raw real-world 3D data (e.g. f…
arXiv cs.CV
TIER_1·Dongliang Cao, Paul Roetzer, Florian Bernard·
arXiv:2310.11420v2 Announce Type: replace Abstract: We propose a novel unsupervised learning approach for non-rigid 3D shape matching. Our approach improves upon recent state-of-the art deep functional map methods and can be applied to a broad range of different challenging scena…
Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncertainty estimation as a passive endpoint for post-…
arXiv:2603.22908v3 Announce Type: replace Abstract: Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transferable knowledge is limited to the predictions o…