Dense-SfM: Structure from Motion with Dense Consistent Matching
This addresses the challenge of achieving dense and accurate 3D reconstruction from multi-view images for computer vision applications, representing an incremental advancement over existing SfM methods.
The paper tackles the problem of limited accuracy and point density in Structure from Motion (SfM) due to sparse keypoint matching, especially in texture-less areas, by introducing Dense-SfM, which integrates dense matching and a Gaussian Splatting-based track extension, resulting in significant improvements in accuracy and density over state-of-the-art methods on ETH3D and Texture-Poor SfM datasets.
We present Dense-SfM, a novel Structure from Motion (SfM) framework designed for dense and accurate 3D reconstruction from multi-view images. Sparse keypoint matching, which traditional SfM methods often rely on, limits both accuracy and point density, especially in texture-less areas. Dense-SfM addresses this limitation by integrating dense matching with a Gaussian Splatting (GS) based track extension which gives more consistent, longer feature tracks. To further improve reconstruction accuracy, Dense-SfM is equipped with a multi-view kernelized matching module leveraging transformer and Gaussian Process architectures, for robust track refinement across multi-views. Evaluations on the ETH3D and Texture-Poor SfM datasets show that Dense-SfM offers significant improvements in accuracy and density over state-of-the-art methods. Project page: https://icetea-cv.github.io/densesfm/.