Performance of modern trackers degrades substantially on transparent objects compared to opaque objects. This is largely due to two distinct reasons. Transparent objects are unique in that their appearance is directly affected by the background. Furthermore, transparent object scenes often contain many visually similar objects (distractors), which often lead to tracking failure. However, development of modern tracking architectures requires large training sets, which do not exist in transparent object tracking. We present two contributions addressing the aforementioned issues. We propose 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. Standard trackers trained on this dataset consistently improve by up to 16%. Our second contribution is a new distractor-aware transparent object tracker (DiTra) that treats localization accuracy and target identification as separate tasks and implements them by a novel architecture. DiTra sets a new state-of-the-art in transparent object tracking and generalizes well to opaque objects.

与不透明物体相比，现代跟踪器的性能在透明物体上显着下降。这主要是由于两个不同的原因。透明对象的独特之处在于它们的外观直接受背景影响。此外，透明物体场景通常包含许多视觉上相似的物体（干扰物），这通常会导致跟踪失败。然而，现代跟踪架构的开发需要大量的训练集，而透明对象跟踪中不存在这种情况。我们针对上述问题提出了两项​​贡献。我们提出了第一个透明对象跟踪训练数据集Trans2k，它由超过 2k 个序列组成，总共有 104,343 个图像，由边界框和分割掩模注释。在此数据集上训练的标准跟踪器持续改进高达 16%。我们的第二个贡献是一种新的干扰感知透明对象跟踪器（DiTra），它将定位精度和目标识别视为单独的任务，并通过新颖的架构来实现它们。 DiTra 在透明对象跟踪方面树立了新的最先进技术，并且可以很好地推广到不透明对象。