Pith. sign in

REVIEW

Sim2Real for Self-Supervised Monocular Depth and Segmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.00238 v1 pith:OZ7ZXQ2K submitted 2020-12-01 cs.CV cs.LG

Sim2Real for Self-Supervised Monocular Depth and Segmentation

classification cs.CV cs.LG
keywords domainrealdatasimulationarchitecturebridgedepthground-truth
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly. While leveraging the power of simulated data can potentially aid in mitigating these costs, networks trained in the simulation domain usually fail to perform adequately when applied to images in the real domain. Recent advances in domain adaptation have indicated that a shared latent space assumption can help to bridge the gap between the simulation and real domains, allowing the transference of the predictive capabilities of a network from the simulation domain to the real domain. We demonstrate that a twin VAE-based architecture with a shared latent space and auxiliary decoders is able to bridge the sim2real gap without requiring any paired, ground-truth data in the real domain. Using only paired, ground-truth data in the simulation domain, this architecture has the potential to generate perception tasks such as depth and segmentation maps. We compare this method to networks trained in a supervised manner to indicate the merit of these results.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.