.png){kind=icon}
.png){kind=icon}
Return
Self-supervised depth super-resolution with contrastive multiview pre-training
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2023.09.023.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Many low-level vision tasks, including guided depth super-resolution (GDSR), struggle with the issue of insufficient paired training data. Self-supervised learning is a promising solution, but it remains challenging to upsample depth maps without the explicit supervision of high-resolution target images. To alleviate this problem, we propose a self-supervised depth super-resolution method with contrastive multiview pre-training. Unlike existing contrastive learning methods for classification or segmentation tasks, our strategy can be applied to regression tasks even when trained on a small-scale dataset and can reduce information redundancy by extracting unique features from the guide. Furthermore, we propose a novel mutual modulation scheme that can effectively compute the local spatial correlation between cross-modal features. Exhaustive experiments demonstrate that our method attains superior performance with respect to state-of-the-art GDSR methods and exhibits good generalization to other modalities.
Keywords:
Depth super-resolution
Self-supervised learning
Contrastive pre-training
Mutual-modulation
Cross-modal
Journal
IF:
6.3
Papers:
7.8K
Citations:
3.0W