Haoyu Ma

Same question. If the authors can provide camera information, that would be very helpful.

Well, it is the problem of the model if self ! You could revise util/MSNet.py like ``` if __name__ == '__main__': x = tf.placeholder(tf.float32, shape = [1, 96, 96, 96,...

> Howie, I'm wondering the same thing. Did you ever make any progress with this? Hi, I don't think the vanilla DECA can support this function. Maybe we can use...

Yes, as this project aims at pose estimation, we always assume that there is a hand in the input image. For hand detection, you may use OpenPose or some other...

Hi, thanks for your interest in our work. Your understanding is correct. We assume the teacher model is a black-box API and we can only access its input-output behavior.

In line 10: self.num_outputs = num_classes * 3

Hi, Thanks for your interest in our work! I uploaded our trained model to Google Drive, here is the [link](https://drive.google.com/drive/folders/1y7ANiDeiIIC2hzrVVndTgYMLDD6Os1HG?usp=sharing). You can also see the evaluation results log inside the...

Another possibility is that there are some issues with S9, as mentioned in https://arxiv.org/pdf/1905.05754.pdf . Thus, I am not sure if you preprocess these data correctly. We follow the default...

There is a patch embedding layer in the middle. The input size of COCO is 256 * 192, while that of MPII is 256 * 256. The CNN backbone downsamples...

For transformer models, actually, the number of parameters can be related to the input size if we use different patch sizes. Besides, if you design a fully forward network, the...