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.
Open Challenges in Deep Stereo: the Booster Dataset / Ramirez, Pierluigi Zama; Tosi, Fabio; Poggi, Matteo; Salti, Samuele; Mattoccia, Stefano; Di Stefano, Luigi. - ELETTRONICO. - (2022), pp. 21136-21146. (Intervento presentato al convegno 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022) tenutosi a New Orleans, LA, USA nel 18-24 June 2022) [10.1109/CVPR52688.2022.02049].
Open Challenges in Deep Stereo: the Booster Dataset
Ramirez, Pierluigi Zama;Tosi, Fabio;Poggi, Matteo;Salti, Samuele;Mattoccia, Stefano;Di Stefano, Luigi
2022
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 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.File | Dimensione | Formato | |
---|---|---|---|
22_CVPR_Ramirez_Open_Challenges_in_Deep_Stereo_The_Booster_Dataset.pdf
accesso aperto
Tipo:
Postprint
Licenza:
Licenza per accesso libero gratuito
Dimensione
902.67 kB
Formato
Adobe PDF
|
902.67 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.