-
Notifications
You must be signed in to change notification settings - Fork 32
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Concerns about comparisons #20
Comments
Hi @DachunKai, thanks for asking this interesting question! To ensure fairness in comparison, we did not include augmentation techniques like de-foggy in our benchmarks. However, we agree that using some de-noising approaches is promising in improving the OoD robustness. Several of our participants in the RoboDepth Challenge have already proven the effectiveness of this two-stage method. You can find more details from the competition report (https://arxiv.org/abs/2307.15061). |
Excellent work!
Would it be appropriate to consider comparing it with two-stage methods that incorporate enhancement algorithms for various common corruption types along with depth estimation? For example, when dealing with foggy conditions, could we explore a comparison with the approach of 'defoggy first, followed by depth estimation'?
The text was updated successfully, but these errors were encountered: