MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00384987" target="_blank" >RIV/68407700:21230/25:00384987 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/WACV61041.2025.00784" target="_blank" >https://doi.org/10.1109/WACV61041.2025.00784</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV61041.2025.00784" target="_blank" >10.1109/WACV61041.2025.00784</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation

Popis výsledku v původním jazyce

In this work, we present MFTIQ, a novel dense long-term tracking model that advances the Multi-Flow Tracker (MFT) framework to address challenges in point-level visual tracking in video sequences. MFTIQ builds upon the flow-chaining concepts of MFT, integrating an Independent Quality (IQ) module that separates correspondence quality estimation from optical flow computations. This decoupling significantly enhances the accuracy and flexibility of the tracking process, allowing MFTIQ to maintain reliable trajectory predictions even in scenarios of prolonged occlusions and complex dynamics. Designed to be "plug-and-play", MFTIQ can be employed with any off-the-shelf optical flow method without the need for fine-tuning or architectural modifications. Experimental validations on the TAPVid Davis dataset show that MFTIQ with RoMa [16] optical flow not only surpasses MFT but also performs comparably to state-of-the-art trackers while having substantially faster processing speed. Code and models available at https://github.com/serycjon/MFTIQ

Název v anglickém jazyce

MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation

Popis výsledku anglicky

In this work, we present MFTIQ, a novel dense long-term tracking model that advances the Multi-Flow Tracker (MFT) framework to address challenges in point-level visual tracking in video sequences. MFTIQ builds upon the flow-chaining concepts of MFT, integrating an Independent Quality (IQ) module that separates correspondence quality estimation from optical flow computations. This decoupling significantly enhances the accuracy and flexibility of the tracking process, allowing MFTIQ to maintain reliable trajectory predictions even in scenarios of prolonged occlusions and complex dynamics. Designed to be "plug-and-play", MFTIQ can be employed with any off-the-shelf optical flow method without the need for fine-tuning or architectural modifications. Experimental validations on the TAPVid Davis dataset show that MFTIQ with RoMa [16] optical flow not only surpasses MFT but also performs comparably to state-of-the-art trackers while having substantially faster processing speed. Code and models available at https://github.com/serycjon/MFTIQ

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

ISBN

979-8-3315-1084-8

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

11

Strana od-do

8079-8089

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Tucson

Datum konání akce

28. 2. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001521272600294