Luciano Muñoz

Is there a way to optimize only the parameters related to the body shape and pose of the smplx model? and therefore, do not fit the parameters related to the...

Hi, if you change lines 83-85 in 'ClientObject.cs' to: ```cs var x = float.Parse(splittedStrings[0],CultureInfo.InvariantCulture.NumberFormat); var y = float.Parse(splittedStrings[1],CultureInfo.InvariantCulture.NumberFormat); var z = float.Parse(splittedStrings[2],CultureInfo.InvariantCulture.NumberFormat); ``` it works in Unity 2021.1

Hi, I'm also testing NormalGAN with my own data from Kinect V2, i think your problem is in depth image pixel values. Modifying 'multiframe_listener.py' example from pylibfreenect2, i save depth...

@Bingoang I use this library for remove background of color image: https://pypi.org/project/rembg/ and after that i removed background of depth using PIL and numpy with: ```python # Open images im_c...

Hi, I'm using 'pylibfreenect2' to capture rgb and depth images from Kinect v2, containing background and body information. I tested NormalGAN with these images, but it fails in erosion function....

Hi, I solved that with this: https://github.com/bharat-b7/IPNet/issues/11

Hi, I was testing Loopreg with pre-trained naked model, using this scan as input: [scan_test.zip](https://github.com/bharat-b7/LoopReg/files/6224037/scan_test.zip) But the input / output looks like this:  I think the...

@wangfudong my mistake, here is the correct one: [scan_correction.zip](https://github.com/bharat-b7/LoopReg/files/6434816/scan_correction.zip)

I ran it, i created a virtual environment with the requirements and modified some paths and it works. whats the error do you have?

@wangfudong, What do you mean by 'offsets'?, Are you removing some offset in SMPL?. Using SMPL+D sounds good, please let me know if you have any results with these.