BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
This provides a valuable resource for researchers in computer vision working on 3D reconstruction, though it is incremental as it builds on existing data collection methods.
The authors tackled the problem of limited training data for multi-view stereo (MVS) networks by introducing BlendedMVS, a large-scale dataset with over 17k high-resolution images, which significantly improved the generalization ability of trained models compared to other datasets.
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}.