Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and high-resolution image datasets is still an open challenge, due to memory and computational constraints. We propose a pipeline which takes advantage of DNNs to improve the quality of 3D reconstructions while being able to handle large and high-resolution datasets. In particular, we propose a confidence prediction network explicitly tailored for Multi-View Stereo (MVS) and we use it for both depth map outlier filtering and depth map refinement within our pipeline, in order to improve the quality of the final 3D reconstructions. We train our confidence prediction network on (semi-)dense ground truth depth maps from publicly available real world MVS datasets. With extensive experiments on popular benchmarks, we show that our overall pipeline can produce state-of-the-art 3D reconstructions, both qualitatively and quantitatively.
@article{arxiv.1912.00439,
title = {DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction},
author = {Andreas Kuhn and Christian Sormann and Mattia Rossi and Oliver Erdler and Friedrich Fraundorfer},
journal= {arXiv preprint arXiv:1912.00439},
year = {2020}
}
Comments
changes in V3: re-worked confidence prediction scheme, re-organized text, updated experiments; changes in V2: a reference was updated