4 papers
3D Gaussian Splatting for Fine-grained Urban Scene Reconstruction via Semantic-guided Density Control and Loss Design
Yueling Liao, San Jiang, Xing Zhang +1
3D Gaussian Splatting (3DGS) has been becoming a promising 3D reconstruction technique because of its advantage of high-fidelity rendering effect with high efficiency. However, it…
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…
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…
Efficient feature matching for UAV images based on compact GPU data scheduling
San Jiang, Kan You, Ruqin Zhou +3
Feature matching dominates the time costs in structure from motion (SfM). The primary contribution of this study is a GPU data schedule algorithm for efficient feature matching of…