Real-World Point Tracking with Verifier-Guided Pseudo-Labeling

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Aydemir, Görkay, Güney, Fatma, Xie, Weidi
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914388042055680
author Aydemir, Görkay
Güney, Fatma
Xie, Weidi
author_facet Aydemir, Görkay
Güney, Fatma
Xie, Weidi
contents Models for long-term point tracking are typically trained on large synthetic datasets. The performance of these models degrades in real-world videos due to different characteristics and the absence of dense ground-truth annotations. Self-training on unlabeled videos has been explored as a practical solution, but the quality of pseudo-labels strongly depends on the reliability of teacher models, which vary across frames and scenes. In this paper, we address the problem of real-world fine-tuning and introduce verifier, a meta-model that learns to assess the reliability of tracker predictions and guide pseudo-label generation. Given candidate trajectories from multiple pretrained trackers, the verifier evaluates them per frame and selects the most trustworthy predictions, resulting in high-quality pseudo-label trajectories. When applied for fine-tuning, verifier-guided pseudo-labeling substantially improves the quality of supervision and enables data-efficient adaptation to unlabeled videos. Extensive experiments on four real-world benchmarks demonstrate that our approach achieves state-of-the-art results while requiring less data than prior self-training methods. Project page: https://kuis-ai.github.io/track_on_r
format Preprint
id arxiv_https___arxiv_org_abs_2603_12217
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Real-World Point Tracking with Verifier-Guided Pseudo-Labeling
Aydemir, Görkay
Güney, Fatma
Xie, Weidi
Computer Vision and Pattern Recognition
Models for long-term point tracking are typically trained on large synthetic datasets. The performance of these models degrades in real-world videos due to different characteristics and the absence of dense ground-truth annotations. Self-training on unlabeled videos has been explored as a practical solution, but the quality of pseudo-labels strongly depends on the reliability of teacher models, which vary across frames and scenes. In this paper, we address the problem of real-world fine-tuning and introduce verifier, a meta-model that learns to assess the reliability of tracker predictions and guide pseudo-label generation. Given candidate trajectories from multiple pretrained trackers, the verifier evaluates them per frame and selects the most trustworthy predictions, resulting in high-quality pseudo-label trajectories. When applied for fine-tuning, verifier-guided pseudo-labeling substantially improves the quality of supervision and enables data-efficient adaptation to unlabeled videos. Extensive experiments on four real-world benchmarks demonstrate that our approach achieves state-of-the-art results while requiring less data than prior self-training methods. Project page: https://kuis-ai.github.io/track_on_r
title Real-World Point Tracking with Verifier-Guided Pseudo-Labeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.12217