作者: Hyojin Kim , Hong Xiao , Nelson Max
DOI: 10.1007/978-3-642-37447-0_15
关键词:
摘要: This paper presents a multi-view stereo algorithm for piecewise planar scene reconstruction and optimization. Our segmentation-based is iterative to minimize our defined energy function, consisting of reconstruction, refinement optimization steps. The first step plane initialization allow each segment have set initial candidates. Then based on non-linear improves the accuracy planes. Finally with segment-adjacency graph leads optimal planes, which chosen among possible candidates by evaluating its relationship adjacent planes in 3D. yields better performance, compared previous algorithms described this paper. results show method suitable outdoor or aerial urban especially wide baselines images textureless regions.