Open Challenges in Deep Stereo: the Booster Dataset

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 netwo...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 21136 - 21146
Main Authors Ramirez, Pierluigi Zama, Tosi, Fabio, Poggi, Matteo, Salti, Samuele, Mattoccia, Stefano, Di Stefano, Luigi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2022
Subjects
Computer vision
Datasets and evaluation; 3D from multi-view and sensors
Labeling
Pattern recognition
Pipelines
Sensors
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary: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 re-lease 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.
ISSN:2575-7075
DOI:10.1109/CVPR52688.2022.02049