3 papers
cs.CV2026
A Large-Scale Dataset and a New Method for RemoteSensing Traffic Object Segmentation
Zhigang Yang, Huiguang Yao, Linmao Tian +2
Remote sensing imagery plays a crucial role in evaluating regional transportation capacity. However, existing segmentation datasets often lack diversity in object categories and sc…
cs.CV2026
VGGT-CD: Training-Free Robust Registration for 3D Change Detection
Wei Zhang, Songhua Li, Yihang Wu +2
3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods predominantly operate in the 2D…
cs.CV2025
Edge Approximation Text Detector
Chuang Yang, Xu Han, Tao Han +3
Pursuing efficient text shape representations helps scene text detection models focus on compact foreground regions and optimize the contour reconstruction steps to simplify the wh…