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

Don't Forget The Past: Recurrent Depth Estimation from Monocular Video

About

Autonomous cars need continuously updated depth information. Thus far, depth is mostly estimated independently for a single frame at a time, even if the method starts from video input. Our method produces a time series of depth maps, which makes it an ideal candidate for online learning approaches. In particular, we put three different types of depth estimation (supervised depth prediction, self-supervised depth prediction, and self-supervised depth completion) into a common framework. We integrate the corresponding networks with a ConvLSTM such that the spatiotemporal structures of depth across frames can be exploited to yield a more accurate depth estimation. Our method is flexible. It can be applied to monocular videos only or be combined with different types of sparse depth patterns. We carefully study the architecture of the recurrent network and its training strategy. We are first to successfully exploit recurrent networks for real-time self-supervised monocular depth estimation and completion. Extensive experiments show that our recurrent method outperforms its image-based counterpart consistently and significantly in both self-supervised scenarios. It also outperforms previous depth estimation methods of the three popular groups. Please refer to https://www.trace.ethz.ch/publications/2020/rec_depth_estimation/ for details.

Vaishakh Patil, Wouter Van Gansbeke, Dengxin Dai, Luc Van Gool• 2020

Related benchmarks

TaskDatasetResultRank
Monocular Depth EstimationKITTI (Eigen)
Abs Rel0.111
502
Depth EstimationKITTI (Eigen split)
RMSE4.148
276
Monocular Depth EstimationKITTI (Eigen split)
Abs Rel0.102
193
Depth PredictionKITTI original ground truth (test)
Abs Rel0.111
38
Depth EstimationKITTI improved ground truth 2015 (93% Eigen split)
Abs Rel0.087
32
Depth EstimationKITTI improved dense ground truth
Abs Rel0.087
29
Depth PredictionKITTI original (Eigen split)
Abs Rel0.111
29
Depth EstimationKITTI Eigen split improved ground truth (test)
Abs Rel0.087
22
Monocular Depth EstimationKITTI Improved Ground Truth 40
Abs Rel Error0.087
22
Depth EstimationKITTI 2015
Abs Rel0.111
21
Showing 10 of 10 rows

Other info

Follow for update