booker-max

icon company University of Science and Technology of China icon location 合肥 icon location interests in low-level vision, event camera, human mesh reconstruction, nerf and point-cloud rendering in autonomous driving scenes.

Results 48 comments of booker-max

Is there a problem with the pre-trained model snapshot_12.pth.tar?

Sorry, I checked my code several times and found no problem. At the same time, when I use snapshot_8.pth.tar, I can get the same result as you, whether it is...

Is there a problem with the pre-trained model snapshot_12.pth.tar?

Thank you for your quick answer.

QuestionsAbout the acquisition of SMPL parameters in the Human3.6M data set

Thank you.

Regarding the calculation of the three indicators The PA MPVPE, PA MPJPE, and F-scores when test on the Freihand dataset

Great! Thank you.

Questions about testing on human3.6M

ok，Thank you!

Questions about testing on human3.6M

I’m sorry to bother you again. I saw a sentence in your paper "Alternatively, we obtain groundtruth SMPL parameters by applying SMPLify-X on the groundtruth 3D joint coordinates of Human3.6M...

Some thoughts on improving the model

1.Okay, does this mean that the performance improvement is small? 2.I use the pre-trained model snapshot_12.pth.tar, the effect is like this ![image](https://user-images.githubusercontent.com/74257220/113248150-7099a300-92cd-11eb-800a-b257f3127d01.png) ![image](https://user-images.githubusercontent.com/74257220/113248482-1f3de380-92ce-11eb-8ff1-03b31a92dc87.png) this is pretty good, but the ten...

Some thoughts on improving the model

Okay, thank you, I will read this article carefully.

how did you use the frei-hand dataset??

Do you have the training code for this paper? Can you share it with me? This is my email address [email protected]，Thank you very much.！

bad result

I also encountered the same problem, have you found a solution now? Do you have the training code for this paper? Can you share it with me? This is my...