DFM4SFM - Dense Feature Matching for Structure from Motion

  • Structure from motion (SfM) is a fundamental task in computer vision and allows recovering the 3D structure of a stationary scene from an image set. Finding robust and accurate feature matches plays a crucial role in the early stages of SfM. So in this work, we propose a novel method for computing image correspondences based on dense feature matching (DFM) using homographic decomposition: The underlying pipeline provides refinement of existing matches through iterative rematching, detection of occlusions and extrapolation of additional matches in critical image areas between image pairs. Our main contributions are improvements of DFM specifically for SfM, resulting in global refinement and global extrapolation of image correspondences between related views. Furthermore, we propose an iterative version of the Delaunay-triangulation-based outlier detection algorithm for robust processing of repeated image patterns. Through experiments, we demonstrate that the proposed method significantlv improves the reconstruction accuracy.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Simon SeibtORCiD, Bartosz von Rymon LipinskiORCiD, Thomas Chang, Marc Erich LatoschikORCiD
DOI:https://doi.org/10.1109/ICIPC59416.2023.10328368
Parent Title (English):2023 IEEE International Conference on Image Processing Challenges and Workshops (ICIPCW)
Document Type:conference proceeding (article)
Language:English
Date of first Publication:2023/11/29
Reviewed:Begutachtet/Reviewed
Release Date:2025/06/02
Pagenumber:5
First Page:3678
Last Page:3682
institutes:Fakultät Informatik
Research Themes:Digitalisierung & Künstliche Intelligenz
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.