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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Depth Estimation | NYU v2 (test) | Threshold Accuracy (delta < 1.25)81.1 | 423 | |
| Monocular Depth Estimation | NYU v2 (test) | Abs Rel0.121 | 257 | |
| Depth Estimation | NYU Depth V2 | RMSE0.586 | 177 | |
| Depth Prediction | NYU Depth V2 (test) | Accuracy (δ < 1.25)81.7 | 113 | |
| Edge accuracy | NYU Depth V2 (test) | Precision79.4 | 30 | |
| Depth Prediction | Make3D C1 (test) | Log10 Error (log10)0.065 | 27 | |
| Depth Estimation | NYUv2 1 (test) | RMSE0.586 | 19 | |
| Depth Estimation | Make3D (C2 error) | Relative Error (rel)0.198 | 17 | |
| Monocular Depth Estimation | Make3D C1 | Abs Rel18.4 | 10 | |
| Depth Estimation | Make3D (test) | C1 RMSE4.38 | 9 |