Question in paper: 1. how to get the mask region as input; 2. Any comparison with ProPainter, just curious

[LokiXun]

For Q1. how to get the mask region as input; Maybe it just doing frame-wise decrease with GT and binarize the mask?

[LIUTIGHE]

1. The mask region in our dataset is extracted by processing difference map between the original frame and the corrupted frame (i.e. morphorlogical, binarize, etc.), which will be introduced in detail in our supplementary materials. In the real application, it requires users to provide frame-wise masks.
2. As of the submission and rebuttal period of our paper, propainter has not released their code, so our paper does not include comparison results with it. But recently we have noticed that influential work and conducted tests. The preliminary test results indicate that propainter can improve, but cannot "revolutionarily" improve the performance of the inpainting method. We believe that one of the main reasons is still the unrecoverable flow in our task setting.