Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation
Authors:
Top Cited Papers
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2619-2627
Abstract
Monocular depth estimation is a challenging task in scene understanding, with the goal to acquire the geometric properties of 3D space from 2D images. Due to the lack of RGB-depth image pairs, unsupervised learning methods aim at deriving depth information with alternative supervision such as stereo pairs. However, most existing works fail to model the geometric structure of objects, which generally results from considering pixel-level objective functions during training. In this paper, we propose SceneNet to overcome this limitation with the aid of semantic understanding from segmentation. Moreover, our proposed model is able to perform region-aware depth estimation by enforcing semantics consistency between stereo pairs. In our experiments, we qualitatively and quantitatively verify the effectiveness and robustness of our model, which produces favorable results against the state-of-the-art approaches do.Keywords
This publication has 20 references indexed in Scilit:
- Semi-Supervised Deep Learning for Monocular Depth Map Prediction2017
- Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks2016
- Depth from Semi-Calibrated Stereo and Defocus2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation2016
- High-Quality Depth from Uncalibrated Small Motion Clip2016
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Towards unified depth and semantic prediction from a single image2015
- Fully convolutional networks for semantic segmentation2015