Learning to Filter Outlier Edges in Global SfM
Keywords: 3D reconstruction, Structure-from-Motion, Translation Averaging
TL;DR: Learned outlier filtering method for translation averaging in global Structure-from-Motion
Abstract: This paper introduces a novel approach to improve camera position estimation in global Structure-from-Motion (SfM) frameworks by filtering inaccurate pose graph edges, representing relative translation estimates, before applying translation averaging. In SfM, pose graph vertices represent cameras and edges relative poses (rotation and translation) between cameras. We formulate the edge filtering problem as a vertex filtering in the dual graph -- a line graph where the vertices stem from edges in the original graph, and the edges from cameras. Exploiting such a representation, we frame the problem as a binary classification over nodes in the dual graph. To learn such a classification and find outlier edges, we employ a Transformer architecture-based technique. To address the challenge of memory overflow often caused by converting to a line graph, we introduce a clustering-based graph processing approach, enabling the application of our method to arbitrarily large pose graphs. The proposed method outperforms existing relative translation filtering techniques in terms of final camera position accuracy and can be seamlessly integrated with any other filter. The code will be made public.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7819
Loading