IP_LAP

IP_LAP copied to clipboard

the lip shakes heavily after training

8

Hello, I trained the landmarks model by the videos I collected from bilibili, running_L1_loss is 0.0066 and running_velocity_loss is 0.0048. but in the inference result, the lip shakes heavily and...

MYTHOFLEGEND

面部会有细微抖动

2

非常感谢您如此出色的工作，在测试之后发现，生成的视频人脸会有很细微的抖动，经过拆帧之后发现，两帧之间生成的区别过大，其中一张下巴很长，像是双下巴或者下巴部分重叠一样，因此产生了面部的抖动，我已经尝试了修改面部平滑的数值，也尝试减小面部检测框的大小，但还是不行，请问您那边有什么思路吗

ruolunhui

can you provided the code for Gaussian-smoothed face mask

madgnot

输出结果抖动强烈和位移的问题

5

输出结果存在严重的位移和强烈抖动的问题，猜测是可能人脸对齐和特征点识别的问题，就是不知道有什么样的改进方案。

zhangziliang04

Lip is so small and can not handle long range face

4

Hi Dear, Your work is so excellent! But after test many videos, I find generated lip is so small and it can not handle long range face. Could you have...

yuanjunchai

https://github.com/Weizhi-Zhong/IP_LAP/assets/156503481/c5566ab9-ae3b-4ee1-8c0a-58c59d3cc369

dousang1999

This file isn't playable. That might be because the file type is unsupported, the file extension is incorrect, or the file is corrupt.

1

After I running inference_single.py. It generated this video https://drive.google.com/file/d/1sJNC_3rjy1Op8aKz4cKBBgbpvkOIlYAx/view?usp=sharing I have debugged the code it stuck here subprocess.call(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) and never reach this line print("succeed output results to:",...

MarehanRefaat

Add `inference.py` and `util`, reconstructed from `inference_single.py`, for better readability and efficiency: - Change parameters of video output (cv2.VideoWriter) for better quality and efficiency. - Minor changes for efficiency, such...

IanLynnEE

Mandarin lip synchronization

2

Hello, thank you very much for opening up this excellent work. When using your code for rendering, we found that the lip synchronization effect in Mandarin is not very good,...

westernbuptboy

finetune question

1

我最近阅读了您的论文，并发现它对该领域做出了有益的贡献。感谢您宝贵的研究成果。 我想知道这个提供的在英文数据集上的预训练模型，是否可以在中文数据集上微调。 是否具有可行性和有效性，是否有任何见解或建议。在将这些模型应用于中文语言时，是否存在任何挑战或需要注意的事项？此外，如果您对于在中文数据上微调的具体技术或方法有任何建议，我将非常感谢您的见解。

Horace-Leon