Lune

ICCV2025顶会

ReTracker: Exploring Image Matching for Robust Online Any Point Tracking

Dongli Tan, Xingyi He, Sida Peng, Yiqing Gong, Xing Zhu, Jiaming Sun, Ruizhen Hu, Yujun Shen, Hujun Bao, Xiaowei Zhou

2025年份
2被引次数

摘要

Figure 1. Comparison Between Existing Online Trackers and the Proposed ReTracker. Retracking target points in a video sequence after long-term occlusions is challenging due to significant scene changes, where current state-of-the-art online trackers often struggle. In contrast, the proposed ReTracker pipeline achieves robust and accurate continuous tracking of target points upon reappearance, effectively handling large viewpoint and appearance variations.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

它引用的顶会 Paper17

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖