Can

Results 10 issues of Can

miss pose instance for person_1 ![102](https://user-images.githubusercontent.com/20749514/168994704-0e35e7eb-8977-4289-9040-2af9a93a1561.jpg) ![102_0](https://user-images.githubusercontent.com/20749514/168994717-2d714ab3-2f58-4095-a161-8469eb5b047e.png) ![102_1](https://user-images.githubusercontent.com/20749514/168994719-8e40e4ab-9809-4dd4-9f0a-2557172c2c16.png) error pose idx ![548](https://user-images.githubusercontent.com/20749514/168994885-86346c70-864a-498e-a4fc-cf02f1292ba9.jpg) ![548_0](https://user-images.githubusercontent.com/20749514/168994895-6a43a4cf-2451-4eef-8570-49d6e26c9363.png) ![548_1](https://user-images.githubusercontent.com/20749514/168994896-dabc2b37-80f1-4299-a9aa-6f7e948349be.png) error mask ![869](https://user-images.githubusercontent.com/20749514/168995020-88df63dc-b1bb-4ed3-bd24-8e8bcefa0e92.jpg) ![869_0](https://user-images.githubusercontent.com/20749514/168995027-05560e48-8671-4939-8d99-589cac946d30.png) ![869_1](https://user-images.githubusercontent.com/20749514/168995033-372dcfa7-79c7-4631-ab8e-88c124a461c3.png) ![869_2](https://user-images.githubusercontent.com/20749514/168995037-c60d62cc-19d3-4d45-9182-2a414460a9c3.png) this is just one example, to tell the truth, there...

for widerface wider_face_train_bbx_gt.txt Number of bounding box x1, y1, w, h, blur, expression, illumination, invalid, occlusion, pose what index does x1 and y1 start, 0 or 1? for celeba list_landmarks_celeba.txt...

I’m confused about how the threshold can be 0.5 for all situations, no matter what M and N is ? if M and N are big enough, f(i, ˆj) can...

It seems the lmk_faces_idx selected to match 68 2D landmark is not so accurate, which can be viewed by Blender as follows: ![Screenshot from 2023-06-19 14-37-19](https://github.com/radekd91/emoca/assets/20749514/c50fa15a-5da3-409b-8593-1db7ac1d63a5) ![Screenshot from 2023-06-19 14-38-28](https://github.com/radekd91/emoca/assets/20749514/e552900e-f1dd-4d78-8f59-8055209e9be9)...

https://github.com/Zejun-Yang/AniPortrait/issues/143

Thanks for sharing this work, good insight and inspiring. But I'm unable to perceive improvement of the pretrained model. My inference of E_expression: For images, inputs: just concat same image...

https://github.com/Zejun-Yang/AniPortrait/issues/143

https://github.com/Zejun-Yang/AniPortrait/issues/143

以下是一些效果展示,包括人脸驱动,语音驱动,表情姿态动作迁移等: https://github.com/Zejun-Yang/AniPortrait/assets/20749514/a4bd2a06-6be8-4ecf-bfa3-337e5dcff4bb https://github.com/Zejun-Yang/AniPortrait/assets/20749514/087b2023-67e9-41bf-bf31-204052889716 https://github.com/Zejun-Yang/AniPortrait/assets/20749514/053533eb-4237-4092-b224-cb62f6b03b59