Measuring the performance of single image depth estimation methods
Authors:
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4150-4157
Abstract
We consider the question of benchmarking the performance of methods used for estimating the depth of a scene from a single image. We describe various measures that have been used in the past, discuss their limitations and demonstrate that each is deficient in one or more ways. We propose a new measure of performance for depth estimation that overcomes these deficiencies, and has a number of desirable properties. We show that in various cases of interest the new measure enables visualisation of the performance of a method that is otherwise obfuscated by existing metrics. Our proposed method is capable of illuminating the relative performance of different algorithms on different kinds of data, such as the difference in efficacy of a method when estimating the depth of the ground plane versus estimating the depth of other generic scene structure. We showcase the method by comparing a number of existing single-view methods against each other and against more traditional depth estimation methods such as binocular stereo.Keywords
This publication has 12 references indexed in Scilit:
- Multi-modal Auto-Encoders as Joint Estimators for Robotics Scene Understanding2016
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture2015
- Deep convolutional neural fields for depth estimation from a single image2015
- Pulling Things out of Perspective2014
- Im2depth: Scalable exemplar based depth transfer2014
- Shape Anchors for Data-Driven Multi-view Reconstruction2013
- Indoor Segmentation and Support Inference from RGBD Images2012
- Make3D: Learning 3D Scene Structure from a Single Still ImageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Machine Learning for High-Speed Corner Detection2006
- Small Vision Systems: Hardware and Implementation1998