A self-supervised method of single-image depth estimation by feeding forward information using max-pooling layers

We propose an encoder–decoder CNN framework to predict depth from one single image in a self-supervised manner. To this aim, we design three kinds of encoder based on the recent advanced deep neural network and one kind of decoder which can generate multiscale predictions. Eight loss functions are d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Visual computer Jg. 37; H. 4; S. 815 - 829
Hauptverfasser: Shi, Jinlong, Sun, Yunhan, Bai, Suqin, Sun, Zhengxing, Tian, Zhaohui
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2021
Springer Nature B.V
Schlagworte:
Artificial Intelligence
Artificial neural networks
Cameras
Coders
Computer Graphics
Computer Science
Deep learning
Estimates
Image contrast
Image Processing and Computer Vision
Image reconstruction
Machine learning
Methods
Neural networks
Original Article
Semantics
Supervision
Encoder–decoder
CNN
Single image
Depth estimation
Self-supervision
ISSN:0178-2789, 1432-2315
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose an encoder–decoder CNN framework to predict depth from one single image in a self-supervised manner. To this aim, we design three kinds of encoder based on the recent advanced deep neural network and one kind of decoder which can generate multiscale predictions. Eight loss functions are designed based on the proposed encoder–decoder CNN framework to validate the performance. For training, we take rectified stereo image pairs as input of the CNN, which is trained by reconstructing image via learning multiscale disparity maps. For testing, the CNN can estimate the accurate depth information by inputting only one single image. We validate our framework on two public datasets in contrast to the state-of-the-art methods and our designed different variants, and the performance of different encoder–decoder architectures and loss functions is evaluated to obtain the best combination, which proves that our proposed method performs very well for single-image depth estimation without the supervision of ground truth.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0178-2789
1432-2315
DOI:10.1007/s00371-020-01832-6