EgoPoints: Advancing Point Tracking for Egocentric Videos

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Darkhalil, Ahmad, Guerrier, Rhodri, Harley, Adam W., Damen, Dima
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915050272325632
author Darkhalil, Ahmad
Guerrier, Rhodri
Harley, Adam W.
Damen, Dima
author_facet Darkhalil, Ahmad
Guerrier, Rhodri
Harley, Adam W.
Damen, Dima
contents We introduce EgoPoints, a benchmark for point tracking in egocentric videos. We annotate 4.7K challenging tracks in egocentric sequences. Compared to the popular TAP-Vid-DAVIS evaluation benchmark, we include 9x more points that go out-of-view and 59x more points that require re-identification (ReID) after returning to view. To measure the performance of models on these challenging points, we introduce evaluation metrics that specifically monitor tracking performance on points in-view, out-of-view, and points that require re-identification. We then propose a pipeline to create semi-real sequences, with automatic ground truth. We generate 11K such sequences by combining dynamic Kubric objects with scene points from EPIC Fields. When fine-tuning point tracking methods on these sequences and evaluating on our annotated EgoPoints sequences, we improve CoTracker across all metrics, including the tracking accuracy $δ^\star_{\text{avg}}$ by 2.7 percentage points and accuracy on ReID sequences (ReID$δ_{\text{avg}}$) by 2.4 points. We also improve $δ^\star_{\text{avg}}$ and ReID$δ_{\text{avg}}$ of PIPs++ by 0.3 and 2.8 respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04592
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EgoPoints: Advancing Point Tracking for Egocentric Videos
Darkhalil, Ahmad
Guerrier, Rhodri
Harley, Adam W.
Damen, Dima
Computer Vision and Pattern Recognition
We introduce EgoPoints, a benchmark for point tracking in egocentric videos. We annotate 4.7K challenging tracks in egocentric sequences. Compared to the popular TAP-Vid-DAVIS evaluation benchmark, we include 9x more points that go out-of-view and 59x more points that require re-identification (ReID) after returning to view. To measure the performance of models on these challenging points, we introduce evaluation metrics that specifically monitor tracking performance on points in-view, out-of-view, and points that require re-identification. We then propose a pipeline to create semi-real sequences, with automatic ground truth. We generate 11K such sequences by combining dynamic Kubric objects with scene points from EPIC Fields. When fine-tuning point tracking methods on these sequences and evaluating on our annotated EgoPoints sequences, we improve CoTracker across all metrics, including the tracking accuracy $δ^\star_{\text{avg}}$ by 2.7 percentage points and accuracy on ReID sequences (ReID$δ_{\text{avg}}$) by 2.4 points. We also improve $δ^\star_{\text{avg}}$ and ReID$δ_{\text{avg}}$ of PIPs++ by 0.3 and 2.8 respectively.
title EgoPoints: Advancing Point Tracking for Egocentric Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.04592