Badour AlBahar
Badour AlBahar
what do you mean by here `images -> normal` and `seg_maps -> normal`? ``` $ ls workplace/sample canonical.obj output transform intrinsics.txt skinning_weight.txt transform_tpose.json normal tex uvmapping.obj ``` I do have...
Can you try using this "transform_tpose.json" instead? I think the issue is due to incorrect transformation. The previous file was not transforming the T-pose to an X-pose. [transform_tpose.json.zip](https://github.com/lingjie0206/Neural_Actor_Main_Code/files/9746966/transform_tpose.json.zip)
Did you modify the code?
I only provided the pretrained model and not the training code. I’ll add it soon. Thanks for your interest.
You can but the results will probably not be great since the model was trained on the DeepFashion dataset. On Fri, Mar 17, 2023 at 7:12 AM Keep Growing And...
The methods builds on dense pose. If dense pose works well with the subjects you have and you have enough data to train on, I think it should work. On...
Make sure that the channels are in the order [i u v]. i as in the body part id and uv are the coordinates.
You can think of it as some sort of copy paste. The mask will tell you the region. You can draw the mask your self of use human parsing to...
When I try SSIM