This repository includes the official project of Mask Guided (MG) Matting, presented in our paper: Mask Guided Matting via Progressive Refinement Network
In your paper you said PRM combines \alpha_{l-1} and \alpha_l' to generate a better \alpha_l.
The idea is cool. However, in the code, I didn't found something like PRN.
In trainer.py Line 185, you get prediction result alpha_pred_os1, alpha_pred_os4, and alpha_pred_os8 from the model. However, alpha_pred_os4 and alpha_pred_os8 are obtained from modules refine_OS4 and refine_OS8 in the decoder directly, which use ONE input.
So, where your g_l, i.e., guidance in your paper? I don't see anything like g_l except obtaining loss like utils.get_unknown_tensor_from_pred.
In your paper you said PRM combines \alpha_{l-1} and \alpha_l' to generate a better \alpha_l.
The idea is cool. However, in the code, I didn't found something like PRN.
In
trainer.py
Line 185, you get prediction resultalpha_pred_os1
,alpha_pred_os4
, andalpha_pred_os8
from the model. However,alpha_pred_os4
andalpha_pred_os8
are obtained from modulesrefine_OS4
andrefine_OS8
in the decoder directly, which use ONE input.So, where your g_l, i.e., guidance in your paper? I don't see anything like g_l except obtaining loss like
utils.get_unknown_tensor_from_pred
.Where your PRM? WHERE YOUR PRM? HAIYAA...