iMVS: Improving MVS Networks by Learning Depth Discontinuities
share
Existing learning-based multi-view stereo (MVS) techniques are effective in terms of completeness in reconstruction. We further improve these techniques by learning depth continuities. Our idea is to jointly estimate the depth and boundary maps. To this end, we introduce learning-based MVS strategies to improve the quality of depth maps via mixture density and depth discontinuity learning. We validate our idea and demonstrate that our strategies can be easily integrated into existing learning-based MVS pipelines where the reconstruction depends on high-quality depth map estimation. We also introduce a bimodal depth representation and a novel spatial regularization approach to the MVS networks. Extensive experiments on various datasets show that our method sets a new state of the art in terms of completeness and overall reconstruction quality. Experiments also demonstrate that the presented model and strategies have good generalization capabilities. The source code will be available soon.
READ FULL TEXT