Unsupervised High-Resolution Depth Learning From Videos With Dual Networks
Preprint
Abstract
Unsupervised depth learning takes the appearance difference between a target view and a view synthesized from its adjacent frame as supervisory signal. Since the supervisory signal only comes from images themselves, the resolution of training data significantly impacts the performance. High-resolution images contain more fine-grained details and provide more accurate supervisory signal. However, due to the limitation of memory and computation power, the original images are typically down-sampled during training, which suffers heavy loss of details and disparity accuracy. In order to fully explore the information contained in high-resolution data, we propose a simple yet effective dual networks architecture, which can directly take high-resolution images as input and generate high-resolution and high-accuracy depth map efficiently. We also propose a Self-assembled Attention (SA-Attention) module to handle low-texture region. The evaluation on the benchmark KITTI and Make3D datasets demonstrates that our method achieves state-of-the-art results in the monocular depth estimation task.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding2019
- Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry2018
- Learning Visual Question Answering by Bootstrapping Hard Attention2018
- DF-Net: Unsupervised Joint Learning of Depth and Flow Using Cross-Task Consistency2018
- Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object DetectionInternational Journal of Computer Vision, 2018
- Discrete-Continuous Depth Estimation from a Single Image2014
- Pulling Things out of Perspective2014
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Single image depth estimation from predicted semantic labels2010
- Active Computer Vision by Cooperative Focus and Stereo1989