# Leveraging AV1 motion vectors for Fast and Dense Feature Matching

arXiv: https://arxiv.org/abs/2510.17434 · HTML: https://mlsanity.com/paper/2510.17434/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 5 of 5)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [A Technical Overview of AV1](https://mlsanity.com/paper/2008.06091/) (2020)

## Built on by (most cited first, 2 of 2)

- [VOCA: Visual Odometry with Codec Awareness](https://mlsanity.com/paper/2607.00189/) (2026)
- [Efficient Dense Matching for Enhanced Gaussian Splatting Using AV1 Motion Vectors](https://mlsanity.com/paper/2605.14629/) (2026)

## Abstract (arXiv)

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.