Polygonal Point Set Tracking

TL;DR

This paper introduces a learning-based polygonal point set tracking method that propagates points along object contours for improved video object segmentation and visual effects, without requiring specialized datasets.

Contribution

It presents a novel point set tracking approach using global-local alignment, a new dataset, and demonstrates superior performance over existing contour-based VOS methods.

Findings

Outperforms baseline and existing contour-based VOS methods

Enables visual effects like part deformation and texture mapping

Introduces a new polygonal point set tracking dataset

Abstract

In this paper, we propose a novel learning-based polygonal point set tracking method. Compared to existing video object segmentation~(VOS) methods that propagate pixel-wise object mask information, we propagate a polygonal point set over frames. Specifically, the set is defined as a subset of points in the target contour, and our goal is to track corresponding points on the target contour. Those outputs enable us to apply various visual effects such as motion tracking, part deformation, and texture mapping. To this end, we propose a new method to track the corresponding points between frames by the global-local alignment with delicately designed losses and regularization terms. We also introduce a novel learning strategy using synthetic and VOS datasets that makes it possible to tackle the problem without developing the point correspondence dataset. Since the existing datasets are not suitable to validate our method, we build a new polygonal point set tracking dataset and demonstrate the superior performance of our method over the baselines and existing contour-based VOS methods. In addition, we present visual-effects applications of our method on part distortion and text mapping.