Skip to Main content Skip to Navigation
Conference papers

P2D: a self-supervised method for depth estimation from polarimetry

Abstract : Monocular depth estimation is a recurring subject in the field of computer vision. Its ability to describe scenes via a depth map while reducing the constraints related to the formulation of perspective geometry tends to favor its use. However, despite the constant improvement of algorithms, most methods exploit only colorimetric information. Consequently, robustness to events to which the modality is not sensitive to, like specularity or transparency, is neglected. In response to this phenomenon, we propose using polarimetry as an input for a self-supervised monodepth network. Therefore, we propose exploiting polarization cues to encourage accurate reconstruction of scenes. Furthermore, we include a term of polarimetric regularization to state-of-the-art method to take specific advantage of the data. Our method is evaluated both qualitatively and quantitatively demonstrating that the contribution of this new information as well as an enhanced loss function improves depth estimation results, especially for specular areas.
Document type :
Conference papers
Complete list of metadatas

Cited literature [36 references]  Display  Hide  Download

https://hal-univ-evry.archives-ouvertes.fr/hal-02977824
Contributor : Désiré Sidibé <>
Submitted on : Monday, October 26, 2020 - 9:56:35 AM
Last modification on : Friday, October 30, 2020 - 3:23:23 AM

File

2020_marc_icpr_2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02977824, version 1

Citation

Marc Blanchon, Désiré Sidibé, Olivier Morel, Ralph Seulin, Daniel Braun, et al.. P2D: a self-supervised method for depth estimation from polarimetry. 25th International Conference on Pattern Recognition (ICPR 2020), Jan 2021, Milan, Italy. ⟨hal-02977824⟩

Share

Metrics

Record views

9

Files downloads

12