The input images and the output silhouettes

ShichenLiu / SoftRas

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

MIT License

1.2k stars 156 forks source link

The input images and the output silhouettes #79

Open Weipeilang opened 3 years ago

Weipeilang commented 3 years ago

How to get the single input image and the rendered silhouettes? For example, input the following image, but the generated silhouettes has multiple models. Do I need to modify anything? test0 test5 @ShichenLiu

ShichenLiu commented 3 years ago

Hi,

Can you describe how you generate the image above? I can hardly help you without more details. Thanks.

Weipeilang commented 3 years ago

ok,I generate the image by this,and the camera is the same as described in this project.Thank you! @ShichenLiu

ShichenLiu commented 3 years ago

Ohh, sorry i didnt make it clear. I meant how you generated the silhouette image on the right side.

Weipeilang commented 3 years ago

I don‘t know, I generated the sihouette as described in the project. This is what I want to ask, how to generate an image with only one sihouette？