Depth prediction is at the core of several computer vision applications, such as autonomous driving and robotics. It is often formulated as a regression task in which depth values are estimated through network layers. Unfortunately, the distribution of values on depth maps is seldom explored. Therefore, this paper proposes a novel framework combining contrastive learning and depth prediction, allowing us to pay more attention to depth distribution and consequently enabling improvements to the overall estimation process. Purposely, we propose a window-based contrastive learning module, which partitions the feature maps into non-overlapping windows and constructs contrastive loss within each one. Forming and sorting positive and negative pairs, then enlarging the gap between the two in the representation space, constraints depth distribution to fit the feature of the depth map. Experiments on KITTI and NYU datasets demonstrate the effectiveness of our framework.

Fan, R., Poggi, M., Mattoccia, S. (2023). Contrastive Learning for Depth Prediction [10.1109/cvprw59228.2023.00325].

Contrastive Learning for Depth Prediction

Fan, Rizhao;Poggi, Matteo;Mattoccia, Stefano
2023

Abstract

Depth prediction is at the core of several computer vision applications, such as autonomous driving and robotics. It is often formulated as a regression task in which depth values are estimated through network layers. Unfortunately, the distribution of values on depth maps is seldom explored. Therefore, this paper proposes a novel framework combining contrastive learning and depth prediction, allowing us to pay more attention to depth distribution and consequently enabling improvements to the overall estimation process. Purposely, we propose a window-based contrastive learning module, which partitions the feature maps into non-overlapping windows and constructs contrastive loss within each one. Forming and sorting positive and negative pairs, then enlarging the gap between the two in the representation space, constraints depth distribution to fit the feature of the depth map. Experiments on KITTI and NYU datasets demonstrate the effectiveness of our framework.
2023
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023)
3226
3237
Fan, R., Poggi, M., Mattoccia, S. (2023). Contrastive Learning for Depth Prediction [10.1109/cvprw59228.2023.00325].
Fan, Rizhao; Poggi, Matteo; Mattoccia, Stefano
File in questo prodotto:
File Dimensione Formato  
Fan_Contrastive_Learning_for_Depth_Prediction_CVPRW_2023_paper.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 5.52 MB
Formato Adobe PDF
5.52 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/11585/961727
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact