I am currently replicating the results of this paper. In this paper they have not mentioned how they are evaluating the results as no ground truth is available for comparison. Same goes for other papers of this topic (unsupervised depth estimation). So I am very much confused about how to evaluate the model for overfitting, underfitting for this.

  • $\begingroup$ Also if the suggestion is lidar scans then how can we use lidar scans as their output is very sparse and many objects are missing from it. $\endgroup$ – Himanshu Feb 22 at 4:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.