DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction

TL;DR

DeepC-MVS introduces a confidence prediction network tailored for multi-view stereo, enhancing 3D reconstruction quality from large, high-resolution datasets by filtering and refining depth maps.

Contribution

It presents a novel confidence prediction network integrated into a pipeline for improved 3D reconstructions from large-scale datasets.

Findings

Achieves state-of-the-art 3D reconstruction quality on benchmarks.

Effectively filters out outlier depth maps using confidence predictions.

Refines depth maps to enhance reconstruction accuracy.

Abstract

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.