Junshu Tang

icon indicating a website link https://junshutang.github.io/ icon indicating an email [email protected]

icon company SJTU icon location Shanghai

Results 6 comments of Junshu Tang

I think I have reached reasonable results, but there are a few questions.

Hi, I wonder if someone has met the same issue like sunken\ambiguous face\hairs\hats\forehead? How can fix it? https://user-images.githubusercontent.com/53079057/160777193-62355302-d000-4eac-a2e2-e9ae8bb86065.mp4 https://user-images.githubusercontent.com/53079057/160777206-cbda8a54-b4b8-4369-b620-358cd6fd7410.mp4 https://user-images.githubusercontent.com/53079057/160777214-4b5ebd96-fdba-43c7-9f42-ae6f66e08617.mp4 https://user-images.githubusercontent.com/53079057/160777260-158416a7-ec8d-4a85-a2f0-8bb9f486a557.mp4 Besides, most of the results seem reasonable. My implementation...

I think I have reached reasonable results, but there are a few questions.

> > I wonder if someone has met the same issue > > Related: > > * [How to fix the sunken face or hairs? #11](https://github.com/NVlabs/eg3d/issues/11) > > though it...

Fail in generating the rendered images

I have the same question as @monicaYang . Where can we find the rendering parameters for 12-view renderer or virtual camera?

Fail in generating the rendered images

Sorry to bother you, I have found the blender script on [https://github.com/jongchyisu/mvcnn_pytorch](url).

python inference.py IndexError: too many indices for array

I have met the same question. My solution is to change: https://github.com/Hangz-nju-cuhk/Rotate-and-Render/blob/956b3a42b3e87c1234b922484f866c21ec5cc252/3ddfa/inference.py#L83 pts_2d_68 = preds[0][0] into pts_2d_68 = preds[0] It works for me.

Some doubts about the results on shapenet55

Sorry for the late reply. We didn't re-train PoinTr. We evaluate its pretrained model on all test set on ShapeNet-55 (no partition) and test different metrics: CD-l1/CD-l2/EMD mentioned in our...