Antonio Loquercio

you can just divide the video in frames, create a "fake" mask, uniformly black, for each image, and run it on our model! Very easy to do! However, you will...

We used the code provided in this repo with the DAVIS checkpoint, so nothing changes with respect to that. We did some fine-tuning on the video to improve performance, always...

I think you might have an issue with image sizes. Are you sure you are running the post-processing on the final resolution (640x480)? Did you use our provided script to...

Do you get the same results as in here http://rpg.ifi.uzh.ch/data/detection_results.zip ? Did you use this [evaluation script](https://github.com/antonilo/unsupervised_detection/blob/master/test_generator.py)? If not, I might need more details to debug the problem (TensorFlow version...

Might be that you used a sub-optimal checkpoint. How many epochs did you train?

Sorry, but it is very difficult to help without details. I would say that the problem is in the way images are pre-processed (reshaping and central cutting). The changes might...

I am not sure how I can help you. Did you use the right model from the model folder http://rpg.ifi.uzh.ch/data/unsupervised_detection_models.zip? Then please do post-processing for obtaining the result published on...

Thanks for pointing it out! However, we are only interested in a normalized flow, not in the flow itself. In fact, a few lines afterward, we normalize it for a...

dear @fyangneil, there are several re-shaping operations in post-processing to make sure that the image resolution is as expected. I would encourage you to check out the readme for details.

please follow the instructions and make sure to reproduce the same results as in here http://rpg.ifi.uzh.ch/data/detection_results.zip