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

Source: [DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction](<https://www.sota2.com/research/paper/68fa682e1e209131cea1a937>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:31:00.251Z

Authors: Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer (2) \_\_INSTITUTION\_5\_\_ Sony Europe B.V., (2) Graz University of Technology, (3) \\'Ecole Polytechnique F\\'ed\\'erale de Lausanne)

Published: 2019-12-01T16:50:07.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-view Stereo on Tanks and Temples (Advanced set)](<https://www.sota2.com/research/sota/multi-view-stereo-on-tanks-and-temples-advanced-set.md>): Multi-view Stereo; Tanks and Temples (Advanced set); Aud. Error: 26.3.

- [Multi-view Stereo on Tanks and Temples Intermediate set](<https://www.sota2.com/research/sota/multi-view-stereo-on-tanks-and-temples-intermediate-set.md>): Multi-view Stereo; Tanks and Temples Intermediate set; Mean F1 Score: 59.79.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1912.00439>)

[PDF](<https://arxiv.org/pdf/1912.00439.pdf>)