3 papers
cs.CV2026
Self-Calibrating Dense Displacement Fields for Reliable Co-Registration of Large Optical Satellite Imagery
Shoukun Sun, Zhe Wang, Sanaz Salati +3
Co-registration underlies nearly every multi-temporal and multi-sensor use of optical satellite imagery, and operational products still carry documented offsets well above the frac…
cs.CV2026
Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinement
San Jiang, Hui Wang, Xing Zhang +5
Integrated 3D reconstruction from aerial-ground images is essential for generating high-precision urban 3D models, yet severe variations in viewpoint, scale, and rotation make robu…
cs.CV2025
Aerial-Ground Image Feature Matching via 3D Gaussian Splatting-based Intermediate View Rendering
Jiangxue Yu, Hui Wang, San Jiang +3
The integration of aerial and ground images has been a promising solution in 3D modeling of complex scenes, which is seriously restricted by finding reliable correspondences. The p…