Qitao Zhao

icon indicating a website link https://qitaozhao.github.io icon indicating an email [email protected]

icon location Pittsburgh icon location Master's student in computer vision at Carnegie Mellon University. Graduated from Shandong University in June 2023.

Results 31 comments of Qitao Zhao

what is the difference for data with and without "occ"?

I have a similar question. What is the difference between the data with "tight" and without for Human3.6m. Thanks for answering.

How to train with pictures from multiple different perspectives

Same question!

Backpropagating through raymarching

@ShengyuH Hi, Shengyu, I wonder if the gradient works properly for camera optimization with the code you provided above? I am trying to do something similar but still encountered `NotImplementedError:...

Is Enable camera pose optimization #83 solved？

Same question here!

Cannot open the download link

Same issue here!

Where is the testing code?

I have the same issue.

About MPI-INF-3DHP

Thanks for your interest! Please refer to [P-STMO](https://github.com/paTRICK-swk/P-STMO). We also follow their implementations.

About MPI-INF-3DHP

Please check [here](https://github.com/QitaoZhao/PoseFormerV2/tree/main/mpi_inf_3dhp) (@HL-KL). I recently got the chance to upload the code. Sorry for the huge delay.

I'm confused about Code

Perhaps the name of `FreqMLP` is a bit confusing. We meant to use this module for the time-domain feature to minor the domain gap. Please leave comments if you have...

the PCK and AUC for MPI-INF-3DHP in PoseFormerV2

Thanks for your comments! We follow [P-STMO](https://github.com/paTRICK-swk/P-STMO) to set up mpi-inf-3dhp dataset. Since we just did some modifications, the code is not included in this repo.