Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking

TL;DR

This paper introduces Trans2k, a large annotated dataset for transparent object tracking, enabling significant performance improvements in deep learning models and fostering new research directions.

Contribution

It presents the first dedicated training dataset for transparent object tracking, including realistic rendering and comprehensive annotations, to advance the field.

Findings

Performance boost of up to 16% with Trans2k training

Dataset includes over 2,000 sequences and 104,343 images

Realistic rendering enhances training effectiveness

Abstract

Visual object tracking has focused predominantly on opaque objects, while transparent object tracking received very little attention. Motivated by the uniqueness of transparent objects in that their appearance is directly affected by the background, the first dedicated evaluation dataset has emerged recently. We contribute to this effort by proposing the first transparent object tracking training dataset Trans2k that consists of over 2k sequences with 104,343 images overall, annotated by bounding boxes and segmentation masks. Noting that transparent objects can be realistically rendered by modern renderers, we quantify domain-specific attributes and render the dataset containing visual attributes and tracking situations not covered in the existing object training datasets. We observe a consistent performance boost (up to 16%) across a diverse set of modern tracking architectures when trained using Trans2k, and show insights not previously possible due to the lack of appropriate training sets. The dataset and the rendering engine will be publicly released to unlock the power of modern learning-based trackers and foster new designs in transparent object tracking.