Code in project is not consistent with content in this paper

In this paper, author said "A common practice to achieve the aforementioned goal is to process face and background independently. As described in Figure 6, they firstly extract aligned faces from the input image and stylize all the faces one-by-one. Then, the background image is rendered with some specialized algorithms and merged with stylized faces to obtain the final result. Instead of using such complex pipeline, we found that our texture translation network can directly render stylized results from full images in one-pass evaluation." However, code in project (https://github.com/menyifang/DCT-Net/blob/main/source/cartoonize.py) shows that, two different models (one for background and one for face) are needed in the inference phase. Meanwhile, when dealing with multi faces in one image, each face need to be aligned, processed and projected to origin position. Each cartoonized face need to be pasted on cartoonized backgound image. In summary, implementation details in this project are totally different with the statement in paper.

Did I misunderstand the code? Or you just released the wrong code?

menyifang / DCT-Net

Code in project is not consistent with content in this paper #25