English

Leveraging AV1 motion vectors for Fast and Dense Feature Matching

Computer Vision and Pattern Recognition 2026-05-15 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2510.17434,
  title  = {Leveraging AV1 motion vectors for Fast and Dense Feature Matching},
  author = {Julien Zouein and Hossein Javidnia and François Pitié and Anil Kokaram},
  journal= {arXiv preprint arXiv:2510.17434},
  year   = {2026}
}

Comments

Accepted ICIR 2025, camera-ready version