BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Networks

TLDR

Deep‑learning multi‑view stereo has achieved impressive results, but the scarcity of large‑scale training data limits model generalization, and collecting such data is costly and labor‑intensive. This work introduces BlendedMVS, a large‑scale dataset designed to supply ample ground‑truth for learning‑based MVS. BlendedMVS is built by reconstructing high‑quality textured meshes from selected scenes, rendering them into color images and depth maps, and blending the rendered colors with the original images to embed realistic ambient lighting for training. The dataset comprises over 17,000 high‑resolution images of diverse scenes, and experiments show that models trained on BlendedMVS generalize significantly better than those trained on existing MVS datasets; the dataset and pretrained models are released on GitHub.

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 https://github.com/YoYo000/BlendedMVS.