.png){kind=icon}
Return
Multi-resolution distillation for self-supervised monocular depth estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2023.11.001.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Obtaining dense depth ground-truth is not trivial, which leads to the introduction of self-supervised monocular depth estimation. Most self-supervised methods utilize the photometric loss as the primary supervisory signal optimize a depth network. However, such self-supervised training often falls into an undesirable local minimum due to the ambiguity of the photometric loss. In this paper, we propose a novel self-distillation training scheme that provides a new self-supervision signal, depth consistency among different input resolutions, to the depth network. We further introduce a gradient masking strategy that adjusts the self-supervision signal of the depth consistency during back-propagation to boost the effectiveness of our depth consistency. Experiments demonstrate that our method brings meaningful performance improvements when applied to various depth network architectures. Furthermore, our method outperforms the existing self-supervised methods on KITTI, Cityscapes, and DrivingStereo datasets by a noteworthy margin.
Keywords:
Monocular depth estimation
Self-supervised learning
Self-distillation
Deep learning
Journal
IF:
3.3
Papers:
8.0K
Citations:
1.6W
Organization
No organization information available
Cited Papers
ShareSaveMeta-analyses of IL1A polymorphisms and the risk of several autoimmune diseases published in databases.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveShareSaveShareSaveShareSaveShareSave
View more