论文标题
Deep Stereo的开放挑战：助推器数据集
Open Challenges in Deep Stereo: the Booster Dataset
论文作者
论文摘要
我们提出了一个新颖的高分辨率和具有挑战性的立体声数据集框架室内场景，并以浓密而准确的地面真相差异注释。我们的数据集特有的是存在几个镜面和透明表面的存在，即最先进的立体声网络失败的主要原因。我们的采集管道利用了一个新型的深层时空立体声框架，该框架可轻松，准确地标记使用子像素精度。我们总共发布了419个样本，这些样本在64个不同的场景中收集，并以密集的地面差异注释。每个样本包括高分辨率对（12 MPX）以及一个不平衡的对（左：12 MPX，右：1.1 MPX）。此外，我们提供手动注释的材料分割面具和15K未标记的样品。我们根据数据集评估了最新的深层网络，强调了它们在解决立体声的开放挑战方面的局限性，并绘制了未来研究的提示。
We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities. Peculiar to our dataset is the presence of several specular and transparent surfaces, i.e. the main causes of failures for state-of-the-art stereo networks. Our acquisition pipeline leverages a novel deep space-time stereo framework which allows for easy and accurate labeling with sub-pixel precision. We release a total of 419 samples collected in 64 different scenes and annotated with dense ground-truth disparities. Each sample include a high-resolution pair (12 Mpx) as well as an unbalanced pair (Left: 12 Mpx, Right: 1.1 Mpx). Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. We evaluate state-of-the-art deep networks based on our dataset, highlighting their limitations in addressing the open challenges in stereo and drawing hints for future research.
