Booster Dataset

Zama Ramirez, Pierluigi ; Tosi, Fabio ; Poggi, Matteo ; Salti, Samuele ; Mattoccia, Stefano ; Di Stefano, Luigi (2022) Booster Dataset. University of Bologna. DOI 10.6092/unibo/amsacta/6876. [Dataset]
Full text disponibile come:
[thumbnail of Booster Dataset Labeled] Archivio (Booster Dataset Labeled)
Licenza: Creative Commons: Attribuzione - Non Commerciale 4.0 (CC BY-NC 4.0)

Download (19GB)
[thumbnail of Booster Dataset Unlabeled] Archivio (Booster Dataset Unlabeled)
Licenza: Creative Commons: Attribuzione - Non Commerciale 4.0 (CC BY-NC 4.0)

Download (50GB)
[thumbnail of README] Documento di testo(rtf) (README)
Licenza: Creative Commons: Attribuzione - Non Commerciale 4.0 (CC BY-NC 4.0)

Download (136kB)

Abstract

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.

Abstract
Tipologia del documento
Dataset
Autori
AutoreAffiliazioneORCID
Zama Ramirez, PierluigiUniversity of Bologna0000-0001-7734-5064
Tosi, FabioUniversity of Bologna0000-0002-6276-5282
Poggi, MatteoUniversity of Bologna0000-0002-3337-2236
Salti, SamueleUniversity of Bologna0000-0001-5609-426X
Mattoccia, StefanoUniversity of Bologna0000-0002-3681-7704
Di Stefano, LuigiUniversity of Bologna0000-0001-6014-6421
Parole chiave
Depth Stereo non-Lambertian Unbalanced High-resolution
Settori scientifico-disciplinari
DOI
Data di deposito
25 Mar 2022 14:24
Ultima modifica
31 Mag 2022 21:00
URI

Altri metadati

Statistica sui download

Statistica sui download

Gestione del documento: Visualizza il documento

^