FDepth: Self-supervised indoor monocular depth estimation via optical flow consistency and feature map synthesis
Authors:
- Xiaotong GuoXGXiaotong Guo
- Huijie ZhaoHZHuijie Zhao
- Shuwei ShaoSSShuwei Shao
- Xudong LiXLXudong Li
- Baochang ZhangBZBaochang Zhang
- 9 April 2024
- journal article
- research article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 133
Abstract
No abstract availableKeywords
This publication has 52 references indexed in Scilit:
- Unsupervised Scale-Consistent Depth Learning from VideoInternational Journal of Computer Vision, 2021
- Unsupervised Learning of Multi-Frame Optical Flow with Occlusions2018
- DF-Net: Unsupervised Joint Learning of Depth and Flow Using Cross-Task Consistency2018
- FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks2017
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- Deep Residual Learning for Image Recognition2016
- Structure-from-Motion Revisited2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Discrete-Continuous Depth Estimation from a Single Image2014
- Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images2013