Michael Bannert

Hi, thanks for the reply! What should I expect the app data folder to be called? There is a "com.nextcloud.client" folder in Android/data. I deleted that one but it did...

Thanks for clarifying. I think I know what you mean. Don't worry - no harm done! :) It's my responsibility after all. Unfortunately, that still didn't solve my problem. I...

Hey Anders, Right, I forgot about each voxel getting its own design matrix. Yes, it makes sense that this is not the highest priority for BROCCOLI. Thanks & best, Michael

I could not update to 3.1.1 using F-Droid on my Pixel 6a. I tried deleting the app after creating a backup file. Reinstalling the app did not work either: I...

I have added the model predictions for the samples shown in Figure 7 of the paper. The problems are easier to see here. The parked cars are falsely predicted to...

The results look a lot better when `test_flow.py` computes the mask in the same way as `test_mask.py` does. I used the default mask threshold of .94 to achieve these results....

To everyone facing the same questions: I made a PR that includes the kind of documentation that I would have found helpful back then. https://github.com/google-research/kubric/pull/307

I have done some further testing and I found out that the code also fails on macOS 12.6 and shows the same artifacts. 

For what it's worth, this is how I circumnavigated PySurfer's problem. I simply plotted both overlays independently, saved them to a PIL image and then used PIL's blend function to...

Dear Eric, Thanks for your comment. I fully agree that overlays should be plotted correctly and it does appear that MNE sees more activity than PySurfer these days. After reading...