Dense-SfM: Structure from Motion with Dense Consistent Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, JongMin, Yoo, Sungjoo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912855161307136
author Lee, JongMin
Yoo, Sungjoo
author_facet Lee, JongMin
Yoo, Sungjoo
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14277
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dense-SfM: Structure from Motion with Dense Consistent Matching
Lee, JongMin
Yoo, Sungjoo
Computer Vision and Pattern Recognition
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/.
title Dense-SfM: Structure from Motion with Dense Consistent Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.14277