Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation

About

This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi- scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through extensive experimental evaluation we demonstrate the effective- ness of the proposed approach and establish new state of the art results on publicly available datasets.

Dan Xu, Elisa Ricci, Wanli Ouyang, Xiaogang Wang, Nicu Sebe• 2017

Related benchmarks

TaskDatasetResultRank
Depth EstimationNYU v2 (test)
Threshold Accuracy (delta < 1.25)81.1
423
Monocular Depth EstimationNYU v2 (test)
Abs Rel0.121
257
Depth EstimationNYU Depth V2
RMSE0.586
177
Depth PredictionNYU Depth V2 (test)
Accuracy (δ < 1.25)81.7
113
Edge accuracyNYU Depth V2 (test)
Precision79.4
30
Depth PredictionMake3D C1 (test)
Log10 Error (log10)0.065
27
Depth EstimationNYUv2 1 (test)
RMSE0.586
19
Depth EstimationMake3D (C2 error)
Relative Error (rel)0.198
17
Monocular Depth EstimationMake3D C1
Abs Rel18.4
10
Depth EstimationMake3D (test)
C1 RMSE4.38
9
Showing 10 of 11 rows

Other info

Code

Follow for update