What's the difference between the DIM and RWP ?

Question

What's the difference between the DIM and RWP ?

Opened this issue 3 years ago · 4 comments

I train the network using the DIM config, but got very poor results, This is my train loss curve, and should i use the RWP config ?

Answer 1 · 2021-07-29T12:20:32.000Z

hi ,Do you have any other problems with your training?

Answer 2 · 2021-07-29T17:39:28.000Z

Hi, if you are training the model for DIM benchmark, please use DIM config, if for real-world portrait images, please use RWP config and the data preparation.

Answer 3 · 2021-08-13T05:46:26.000Z

why comp weight set to 0 in config file, why not use comp loss to train network

Answer 4 · 2021-08-16T16:53:40.000Z

why comp weight set to 0 in config file, why not use comp loss to train network

As mentioned in the paper, during RWP training the composited input is heavily augmented (e.g. with noise), whereas in the compositional loss it would be compared against a blend of clean, non-augmented source background and foreground, which makes no sense.