MFTIQ提升视频点级追踪精度，支持长时间遮挡与复杂运动。
MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation
- 分离光流计算与匹配质量评估，提升追踪灵活性
- 在TAP-Vid Davis数据集上速度更快且精度优于MFT
- 可无缝接入任意现成光流模型，无需调参或修改结构
本文提出MFTIQ，一种新型密集长时视频点级追踪模型，基于Multi-Flow Tracker（MFT）框架改进。MFTIQ沿用流链机制，引入独立质量（IQ）模块，将对应关系质量估计与光流计算解耦。这一设计显著提升追踪准确率与灵活性，使模型在长期遮挡和复杂动态场景下仍能保持可靠轨迹预测。该方法具有‘即插即用’特性，可兼容任意现成光流算法，无需微调或架构修改。在TAP-Vid Davis数据集上的实验表明，采用RoMa光流的MFTIQ不仅超越MFT，性能接近当前最优追踪器，同时处理速度显著更快。代码与模型开源于https://github.com/serycjon/MFTIQ。
原文摘要 · Abstract (English)
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 TAP-Vid Davis dataset show that MFTIQ with RoMa 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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。