CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xian, Ruiqi, Patel, Deep, Melvin, Iain, Kundu, Sanjoy, Min, Martin Renqiang, Manocha, Dinesh
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918492925591552
author Xian, Ruiqi
Patel, Deep
Melvin, Iain
Kundu, Sanjoy
Min, Martin Renqiang
Manocha, Dinesh
author_facet Xian, Ruiqi
Patel, Deep
Melvin, Iain
Kundu, Sanjoy
Min, Martin Renqiang
Manocha, Dinesh
contents Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this paper, we present CalibFree, a self-supervised representation learning framework that does not need any calibration or manual labeling for the MCMOT task. By promoting feature separation between view-agnostic and view-specific representations through single-view distillation and cross-view reconstruction, our method adapts to complex, dynamic scenarios with minimal overhead. Experiments on the MMP-MvMHAT dataset show a 3% improvement in overall accuracy and a 7.5% increase in the average F1 score over state-of-the-art approaches, confirming the effectiveness of our calibration-free design. Moreover, on the more diverse MvMHAT dataset, our approach demonstrates superior over-time tracking and strong cross-view performance, highlighting its adaptability to a wide range of camera configurations. Code will be publicly available upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09245
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking
Xian, Ruiqi
Patel, Deep
Melvin, Iain
Kundu, Sanjoy
Min, Martin Renqiang
Manocha, Dinesh
Computer Vision and Pattern Recognition
Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this paper, we present CalibFree, a self-supervised representation learning framework that does not need any calibration or manual labeling for the MCMOT task. By promoting feature separation between view-agnostic and view-specific representations through single-view distillation and cross-view reconstruction, our method adapts to complex, dynamic scenarios with minimal overhead. Experiments on the MMP-MvMHAT dataset show a 3% improvement in overall accuracy and a 7.5% increase in the average F1 score over state-of-the-art approaches, confirming the effectiveness of our calibration-free design. Moreover, on the more diverse MvMHAT dataset, our approach demonstrates superior over-time tracking and strong cross-view performance, highlighting its adaptability to a wide range of camera configurations. Code will be publicly available upon acceptance.
title CalibFree: Self-Supervised View Feature Separation for Calibration-Free Multi-Camera Multi-Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.09245