BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

TL;DR

BlendedMVS is a large-scale dataset created using 3D reconstruction and blending techniques, significantly improving the generalization of deep learning models for multi-view stereo tasks.

Contribution

The paper introduces BlendedMVS, a novel large-scale MVS dataset generated through a new pipeline, enhancing training data availability and model generalization.

Findings

Models trained on BlendedMVS generalize better to unseen scenes.

The dataset contains over 17,000 high-resolution images from diverse environments.

Extensive experiments validate the dataset's effectiveness in improving MVS performance.

Abstract

While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures. In this paper, we introduce BlendedMVS, a novel large-scale dataset, to provide sufficient training ground truth for learning-based MVS. To create the dataset, we apply a 3D reconstruction pipeline to recover high-quality textured meshes from images of well-selected scenes. Then, we render these mesh models to color images and depth maps. To introduce the ambient lighting information during training, the rendered color images are further blended with the input images to generate the training input. Our dataset contains over 17k high-resolution images covering a variety of scenes, including cities, architectures, sculptures and small objects. Extensive experiments demonstrate that BlendedMVS endows the trained model with significantly better generalization ability compared with other MVS datasets. The dataset and pretrained models are available at \url{https://github.com/YoYo000/BlendedMVS}.