ProTracker：用於穩健和精確點跟蹤的概率集成

摘要

本文提出了一個名為ProTracker的新型框架，用於在影片中對任意點進行堅固且準確的長期密集追蹤。我們方法的關鍵思想是將概率積分納入其中，以精煉來自光流和語義特徵的多個預測，實現對短期和長期追蹤的堅固支持。具體來說，我們以概率方式整合光流估計，通過最大化每個預測的可能性，生成平滑且準確的軌跡。為了有效地重新定位由於遮擋而消失和重新出現的具有挑戰性的點，我們進一步將長期特徵對應納入我們的光流預測中，以進行連續軌跡生成。大量實驗表明，ProTracker在無監督和自監督方法中實現了最先進的性能，甚至在幾個基準測試中勝過監督方法。我們的程式碼和模型將在發表後公開提供。

English

In this paper, we propose ProTracker, a novel framework for robust and accurate long-term dense tracking of arbitrary points in videos. The key idea of our method is incorporating probabilistic integration to refine multiple predictions from both optical flow and semantic features for robust short-term and long-term tracking. Specifically, we integrate optical flow estimations in a probabilistic manner, producing smooth and accurate trajectories by maximizing the likelihood of each prediction. To effectively re-localize challenging points that disappear and reappear due to occlusion, we further incorporate long-term feature correspondence into our flow predictions for continuous trajectory generation. Extensive experiments show that ProTracker achieves the state-of-the-art performance among unsupervised and self-supervised approaches, and even outperforms supervised methods on several benchmarks. Our code and model will be publicly available upon publication.

ProTracker：用於穩健和精確點跟蹤的概率集成

ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

摘要

Summary

Support