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

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

About

Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner. Recent approaches to single view depth estimation explore the possibility of learning without full supervision via minimizing photometric error. In this paper, we explore the use of stereo sequences for learning depth and visual odometry. The use of stereo sequences enables the use of both spatial (between left-right pairs) and temporal (forward backward) photometric warp error, and constrains the scene depth and camera motion to be in a common, real-world scale. At test time our framework is able to estimate single view depth and two-view odometry from a monocular sequence. We also show how we can improve on a standard photometric warp loss by considering a warp of deep features. We show through extensive experiments that: (i) jointly training for single view depth and visual odometry improves depth prediction because of the additional constraint imposed on depths and achieves competitive results for visual odometry; (ii) deep feature-based warping loss improves upon simple photometric warp loss for both single view depth estimation and visual odometry. Our method outperforms existing learning based methods on the KITTI driving dataset in both tasks. The source code is available at https://github.com/Huangying-Zhan/Depth-VO-Feat

Huangying Zhan, Ravi Garg, Chamara Saroj Weerasekera, Kejie Li, Harsh Agarwal, Ian Reid• 2018

Related benchmarks

TaskDatasetResultRank
Monocular Depth EstimationKITTI (Eigen)
Abs Rel0.135
502
Depth EstimationKITTI (Eigen split)
RMSE5.585
276
Monocular Depth EstimationKITTI
Abs Rel0.144
161
Monocular Depth EstimationKITTI 80m maximum depth (Eigen)
Abs Rel0.144
126
Monocular Depth EstimationKITTI 2015 (Eigen split)
Abs Rel0.135
95
Depth PredictionKITTI original ground truth (test)
Abs Rel0.135
38
Depth EstimationKITTI improved ground truth 2015 (93% Eigen split)
Abs Rel0.13
32
Single-view depth estimationKITTI raw (test)
AbsRel0.144
24
Depth EstimationKITTI Eigen split improved ground truth (test)
Abs Rel0.13
22
Monocular Depth EstimationKITTI Improved Ground Truth 40
Abs Rel Error0.13
22
Showing 10 of 20 rows

Other info

Follow for update