EC-SfM: Efficient Covisibility-based Structure-from-Motion for Both Sequential and Unordered Images
This addresses the efficiency gap in 3D reconstruction for computer vision applications, particularly for unordered Internet images, though it is incremental as it builds on existing SfM methods.
The paper tackles the problem of slow Structure-from-Motion (SfM) for unordered images by proposing a unified framework that uses covisibility and registration dependency to efficiently reconstruct sequential, unordered, and mixed image data, achieving three times faster feature matching and an order of magnitude faster reconstruction without accuracy loss.
Structure-from-Motion is a technology used to obtain scene structure through image collection, which is a fundamental problem in computer vision. For unordered Internet images, SfM is very slow due to the lack of prior knowledge about image overlap. For sequential images, knowing the large overlap between adjacent frames, SfM can adopt a variety of acceleration strategies, which are only applicable to sequential data. To further improve the reconstruction efficiency and break the gap of strategies between these two kinds of data, this paper presents an efficient covisibility-based incremental SfM. Different from previous methods, we exploit covisibility and registration dependency to describe the image connection which is suitable to any kind of data. Based on this general image connection, we propose a unified framework to efficiently reconstruct sequential images, unordered images, and the mixture of these two. Experiments on the unordered images and mixed data verify the effectiveness of the proposed method, which is three times faster than the state of the art on feature matching, and an order of magnitude faster on reconstruction without sacrificing the accuracy. The source code is publicly available at https://github.com/openxrlab/xrsfm