Saved in:
Bibliographic Details
Main Authors: Zouein, Julien, Javidnia, Hossein, Pitié, François, Kokaram, Anil
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.17434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913127925284864
author Zouein, Julien
Javidnia, Hossein
Pitié, François
Kokaram, Anil
author_facet Zouein, Julien
Javidnia, Hossein
Pitié, François
Kokaram, Anil
contents We repurpose AV1 motion vectors to produce dense sub-pixel correspondences and short tracks filtered by cosine consistency. On short videos, this compressed-domain front end runs comparably to sequential SIFT while using far less CPU, and yields denser matches with competitive pairwise geometry. As a small SfM demo on a 117-frame clip, MV matches register all images and reconstruct 0.46-0.62M points at 0.51-0.53,px reprojection error; BA time grows with match density. These results show compressed-domain correspondences are a practical, resource-efficient front end with clear paths to scaling in full pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17434
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging AV1 motion vectors for Fast and Dense Feature Matching
Zouein, Julien
Javidnia, Hossein
Pitié, François
Kokaram, Anil
Computer Vision and Pattern Recognition
We repurpose AV1 motion vectors to produce dense sub-pixel correspondences and short tracks filtered by cosine consistency. On short videos, this compressed-domain front end runs comparably to sequential SIFT while using far less CPU, and yields denser matches with competitive pairwise geometry. As a small SfM demo on a 117-frame clip, MV matches register all images and reconstruct 0.46-0.62M points at 0.51-0.53,px reprojection error; BA time grows with match density. These results show compressed-domain correspondences are a practical, resource-efficient front end with clear paths to scaling in full pipelines.
title Leveraging AV1 motion vectors for Fast and Dense Feature Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.17434