As reported in the stereo literature, confidence estimation represents a powerful cue to detect outliers as well as to improve depth accuracy. Purposely, we proposed a strategy enabling us to achieve state-of-the-art results by learning a confidence measure in the disparity domain only with a CNN. Since this method does not require the cost volume, it is very appealing because potentially suited for any depth-sensing technologies, including, for instance, those based on deep networks. By following this intuition, in this paper, we deeply investigate the performance of confidence estimation methods, known in the literature and new ones proposed in this paper, neglecting the use of the cost volume. Specifically, we estimate from scratch confidence measures feeding deep networks with raw depth estimates and optionally images and assess their performance deploying three datasets and three stereo algorithms. We also investigate, for the first time, their performance with disparity maps inferred by deep stereo end-to-end architectures. Moreover, we move beyond the stereo matching context, estimating confidence from depth maps generated by a monocular network. Our extensive experiments with different architectures highlight that inferring confidence prediction from the raw reference disparity only, as proposed in our previous work, is not only the most versatile solution but also the most effective one in most cases.

Poggi, M., Tosi, F., Mattoccia, S. (2020). Good cues to learn from scratch a confidence measure for passive depth sensors. IEEE SENSORS JOURNAL, 20(22), 13533-13541 [10.1109/JSEN.2020.3004629].

Good cues to learn from scratch a confidence measure for passive depth sensors

Poggi, Matteo;Tosi, Fabio;Mattoccia, Stefano
2020

Abstract

As reported in the stereo literature, confidence estimation represents a powerful cue to detect outliers as well as to improve depth accuracy. Purposely, we proposed a strategy enabling us to achieve state-of-the-art results by learning a confidence measure in the disparity domain only with a CNN. Since this method does not require the cost volume, it is very appealing because potentially suited for any depth-sensing technologies, including, for instance, those based on deep networks. By following this intuition, in this paper, we deeply investigate the performance of confidence estimation methods, known in the literature and new ones proposed in this paper, neglecting the use of the cost volume. Specifically, we estimate from scratch confidence measures feeding deep networks with raw depth estimates and optionally images and assess their performance deploying three datasets and three stereo algorithms. We also investigate, for the first time, their performance with disparity maps inferred by deep stereo end-to-end architectures. Moreover, we move beyond the stereo matching context, estimating confidence from depth maps generated by a monocular network. Our extensive experiments with different architectures highlight that inferring confidence prediction from the raw reference disparity only, as proposed in our previous work, is not only the most versatile solution but also the most effective one in most cases.
2020
Poggi, M., Tosi, F., Mattoccia, S. (2020). Good cues to learn from scratch a confidence measure for passive depth sensors. IEEE SENSORS JOURNAL, 20(22), 13533-13541 [10.1109/JSEN.2020.3004629].
Poggi, Matteo; Tosi, Fabio; Mattoccia, Stefano
File in questo prodotto:
File Dimensione Formato  
CCNN_sensors.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 9.05 MB
Formato Adobe PDF
9.05 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/763874
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact