SDE-DualENet: A Novel Dual Efficient Convolutional Neural Network for Robust Stereo Depth Estimation

Stereo depth estimation is dependent on optimal correspondence matching between pixels of stereo-pair image to infer depth. In this paper, we attempt to revisit the stereo depth estimation problem in a simple dual convolutional neural network (CNN) based on EfficientNet that avoids the construction...

Full description

Saved in:
Bibliographic Details
Main Authors: Anil, Rithvik, Sharma, Mansi, Choudhary, Rohit
Format: Conference Proceeding
Language:English
Subjects:
Codes
Costs
Estimation
Image processing
Poles and towers
Prediction algorithms
Visual communication
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Stereo depth estimation is dependent on optimal correspondence matching between pixels of stereo-pair image to infer depth. In this paper, we attempt to revisit the stereo depth estimation problem in a simple dual convolutional neural network (CNN) based on EfficientNet that avoids the construction of a cost volume in stereo matching. This has been performed by considering different weights in otherwise identical towers of the CNN. The proposed algorithm is dubbed as SDE-DualENet. The architecture of SDE-DualENet eliminates the construction of cost-volume by learning to match correspondence between pixels with a different set of weights in the dual towers. The results are demonstrated on complex scenes with high details and large depth variations. The SDE-DualENet depth prediction network outperforms state-of-the-art monocular and stereo depth estimation methods, both qualitatively and quantitatively on challenging scene flow dataset. The code and pre-trained models will be made publicly available.
ISSN:2642-9357
DOI:10.1109/VCIP53242.2021.9675391