1. DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
- Author
-
Zhou Liyang, Zhuang Zhang, Sun Han, Zhang Guofeng, Jiang Hanqing, and Bao Hujun
- Subjects
Surface (mathematics) ,surface meshing ,Image View ,business.industry ,Computer science ,Science ,3D reconstruction ,Point cloud ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,multi-view reconstruction ,detail preserving ,depth estimation ,Completeness (order theory) ,Benchmark (computing) ,General Earth and Planetary Sciences ,Computer vision ,Artificial intelligence ,Scale (map) ,business ,Surface reconstruction ,ComputingMethodologies_COMPUTERGRAPHICS - Abstract
This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structures, especially for linear objects. Our framework begins with a sparse reconstruction carried out by an incremental Structure-from-Motion. Based on the reconstructed sparse map, a novel detail preserving PatchMatch approach is applied for depth estimation of each image view. The estimated depth maps of multiple views are then fused to a dense point cloud in a memory-efficient way, followed by a detail-aware surface meshing method to extract the final surface mesh of the captured scene. Experiments on ETH3D benchmark show that the proposed method outperforms other state-of-the-art methods on F1-score, with the running time more than 4 times faster. More experiments on large-scale photo collections demonstrate the effectiveness of the proposed framework for large-scale scene reconstruction in terms of accuracy, completeness, memory saving, and time efficiency.
- Published
- 2021