Hengda Li

The reconstructed image is strange

2

When I tried to use the PTI optimization model and run the inference_on_Videos. py file, the adhesion effect of the video result was too obvious, like pulling gum. In a...

I need to calculate the loss of adjacent frames in a region of the image at 1024 resolution, should I interpolate the resulting mask to 1024 size？

About Video Hair Editing

1

Thanks you for you great works! Do you think video hair editing based on HairCLIP is achievable？ I have a little try, but the region of hairstyle still hard to...

Hi! thanks for you great works. Is there anything in here that the title says?

What is the size of the style code in global directions

1

 I am curious about the size of the style code . And after we got Δs， should we normalize it to a unit norm?

Why requirments.txt is empty

1

I want to run this project , but the environment disturbs me because that file is empty. How did everyone else install it ? Who can help me.I am a...

I want to use CAM to analyze the network's attention to each frame in gait recognition tasks. The inputs video size is (B=1,T,H,W). After extracting features from each frame through...

Why do you want to edit objects in the first place rather than human body or face? I have seen a lot of non-human editing, is there have a big...

How long did you train on each data set, and what GPU (8*1080Ti?) did you train on?

Hi! Thanks for your great work! I have a question about the input skeleton data. Hrnet give a joint two dims (x,y)? what is the 3rd dim means?