Back to Search
Start Over
Self-supervised depth super-resolution with contrastive multiview pre-training.
- Source :
-
Neural Networks . Nov2023, Vol. 168, p223-236. 14p. - Publication Year :
- 2023
-
Abstract
- 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. • We propose a self-supervised method for depth upsampling with contrastive multiview pre-training. • In the pre-training, we develop an autoencoder-based framework with contrastive and reconstruction losses. • We propose a novel mutual modulation scheme. • Experimental results demonstrate the superiority of the proposed method against SOTA methods. [ABSTRACT FROM AUTHOR]
- Subjects :
- *GENERALIZATION
*CLASSIFICATION
Subjects
Details
- Language :
- English
- ISSN :
- 08936080
- Volume :
- 168
- Database :
- Academic Search Index
- Journal :
- Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 173474647
- Full Text :
- https://doi.org/10.1016/j.neunet.2023.09.023