The lips regressor predicts unexpected result about audio2photoreal HOT 5 CLOSED

If someone is trying to reproduce the video above, here is my render code.

from matplotlib import pyplot as plt
import cv2
import numpy as np
from tqdm import tqdm
import os

def plot_3d(scatters, frame_id):
    fig = plt.figure()
    ax = fig.add_subplot(111, projection='3d')
    # set the ax border
    ax.set_xlim(border[0], border[1])
    ax.set_ylim(border[2], border[3])
    ax.set_zlim(border[4], border[5])
    ax.set_box_aspect([1, 1, 1])

    ax.scatter(scatters[0], scatters[1], scatters[2])
    # save the plot as image
    plt.savefig('./rendered/lips_{:06d}.png'.format(frame_id))
    plt.close()


if __name__ == '__main__':
    npy_file_name = 'lips_vertice_causal.npy'
    save_name = 'lips_causal.avi'

    if os.path.exists('./rendered'):
        os.system('rm -r ./rendered')
    os.makedirs('./rendered')

    data = np.load(npy_file_name).reshape(-1, 338, 3)
    # print(data.shape)
    x, y, z = data[..., 0], data[..., 1], data[..., 2]
    # print(x.shape, y.shape, z.shape)
    border = [x.min(), x.max(), y.min(), y.max(), z.min(), z.max()]
    # print(border)
    for idx in tqdm(range(x.shape[0]), desc='plotting'):
        plot_3d([x[idx, :], y[idx, :], z[idx, :]], idx)

    # save as video
    img = cv2.imread('./rendered/lips_000000.png')
    h, w, _ = img.shape
    fourcc = cv2.VideoWriter_fourcc(*'XVID')
    video = cv2.VideoWriter(save_name, fourcc, 30, (w, h))
    for i in tqdm(range(x.shape[0]), desc='writing video'):
        video.write(cv2.imread('./rendered/lips_{:06d}.png'.format(i)))
    video.release()
    cv2.destroyAllWindows()

from audio2photoreal.

Hi and thanks for your interest in our work! To your questions:

1. Yeah, it's not really an encoder-decoder structure, it's really just a single straight-through network. As you can see, the transformer decoder does not receive informative input, only zeros:

   audio2photoreal/model/diffusion.py

   Line 74 in 3a94699

   x = torch.zeros(B, T, 512, device=audio.device)

   
   So, in other words, the audio-to-lip module is just a regressor that goes from wav2vec to vertex space with a few transformer-style operations. The architecture looks a bit confusing, which is an artifact of other experiments to make the module not a regressor but an actual diffusion model. You can just ignore this :)

2. No attention mask. Correct. Our whole framework is an acausal model, so there is no need to induce causality in the audio encodings or in the lip regressor.

3. Lip vertex visualization. The model doesn't predict the vertices in its original vertex space, but in a z-normalized space (so each vertex has zero mean and unit variance). If you'd want to see the actual lip vertices, you'd have to revert that transformation. Is this something you need? In that case I could see to dig it up for you.

from audio2photoreal.

Thank you so much for replying. I guess transforming to z-normed space will benefit training, is that correct?

If convenient, I would appreciate it if you could show me how to revert to the original vertex space.

Many thanks :)

from audio2photoreal.

Hey! The version of the lip regressor used in here actually uses a more complex decoding from the lip vertex space that you plotted which we unfortunately can't provide publicly since you would be able to render lip-information of participants that are not approved for public release. Sorry :(

from audio2photoreal.

Thanks for replying! Closing the issue as the lips regressor is making a reasonable prediction.

from audio2photoreal.