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

Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics

About

We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically, we model the motion of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. [AAAI'19]. Code and models have been open sourced at https://sites.google.com/corp/view/struct2depth.

Vincent Casser, Soeren Pirk, Reza Mahjourian, Anelia Angelova• 2019

Related benchmarks

TaskDatasetResultRank
Depth EstimationKITTI (Eigen split)
RMSE4.7503
276
Monocular Depth EstimationKITTI (test)
Abs Rel Error0.1529
103
Monocular Depth EstimationCityscapes
Accuracy (delta < 1.25)82.6
62
Depth PredictionCityscapes (test)
RMSE7.0237
52
Depth EstimationCityscapes (test)--
40
Depth EstimationKITTI 50m cap (test)
Abs Rel0.103
24
Monocular Depth EstimationCityscapes (test)
Abs Rel Error0.145
11
Monocular Depth EstimationCityscapes 12 (test)
Abs Rel0.145
11
Depth EstimationKITTI 80m cap revised evaluation code (test)
Abs Rel0.1108
9
Showing 9 of 9 rows

Other info

Code

Follow for update