Monocular Depth Estimation Using Relative Depth Maps
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9721-9730
Abstract
We propose a novel algorithm for monocular depth estimation using relative depth maps. First, using a convolutional neural network, we estimate relative depths between pairs of regions, as well as ordinary depths, at various scales. Second, we restore relative depth maps from selectively estimated data based on the rank-1 property of pairwise comparison matrices. Third, we decompose ordinary and relative depth maps into components and recombine them optimally to reconstruct a final depth map. Experimental results show that the proposed algorithm provides the state-of-art depth estimation performance.Keywords
This publication has 49 references indexed in Scilit:
- Deep learning for detecting robotic graspsThe International Journal of Robotics Research, 2015
- Depth Transfer: Depth Extraction from Video Using Non-Parametric SamplingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Real-time human pose recognition in parts from single depth imagesCommunications of the ACM, 2013
- Realtime Depth Estimation and Obstacle Detection from Monocular Video2006
- Depth estimation and image restoration using defocused stereo pairsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Colorization using optimizationACM Transactions on Graphics, 2004
- Regularized symmetric indefinite systems in interior point methods for linear and quadratic optimizationOptimization Methods and Software, 1999
- Least squares quantization in PCMIEEE Transactions on Information Theory, 1982
- A scaling method for priorities in hierarchical structuresJournal of Mathematical Psychology, 1977