Deeper Monocular Depth Prediction via Long and Short Skip Connection
- Resource Type
- Conference
- Authors
- Wang, Zhaokai; Xiao, Limin; Xu, Rongbin; Su, Shubin; Li, Shupan; Song, Yao
- Source
- 2019 International Joint Conference on Neural Networks (IJCNN) Neural Networks (IJCNN), 2019 International Joint Conference on. :1-7 Jul, 2019
- Subject
- Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Feature extraction
Task analysis
Convolution
Predictive models
Image resolution
Deconvolution
Computational modeling
Depth prediction
convolutional neural work
residual learning
- Language
- ISSN
- 2161-4407
This paper presents a fully convolutional neural network to tackle the mapping between single view RGB images and depth maps. To regress the depth maps from monocular images, we leverage deep short skip connections in residual learning for extracting features rather than using hand-crafted features. We further propose long skip connections in up-sampling stage to reuse the feature maps which is proved to enhance the result experimentally. To show the impact of loss functions in monocular depth map predictions, we train our model with kind of loss functions and compare the results qualitatively and quantitatively. The proposed model outperforms all current state-of-the-art results with less training data as well as less than half of training epochs in two standard benchmark data sets without any post-processing procedures or other refinement steps.