High-resolution multi-view stereo with multi-scale feature fusion

Abstract

To enhance the handling of three-dimensional reconstruction for large-scale scenes and high-resolution images, we introduce a novel multi-view high-resolution three-dimensional reconstruction approach. Our proposed method integrates a Feature Pyramid Network with the Swin Transformer for improved performance. We integrate the Swin Transformer into the feature pyramid. This integration aims to establish long-range feature dependencies, facilitate information exchange between different input positions, and enhance the global consistency of feature representation. This improves the efficiency of the feature extraction stage. Following this, we apply cost volume regularization to mitigate noise and compute depth maps. A Depth Optimization Module is employed to refine the predicted depth maps, thereby enhancing their precision. Experimental results demonstrate the efficacy of our method in generating more accurate depth information, particularly in predicting high-resolution depth maps. Our approach utilizes these depth predictions to generate point clouds, enabling precise matching and reconstruction of multi-view images. Experiments conducted on public datasets validate the effectiveness and superiority of our proposed method.