TRUST icon indicating copy to clipboard operation
TRUST copied to clipboard

Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (ECCV2022)

Results 8 TRUST issues
Sort by recently updated
recently updated
newest added

Hello, thanks for the project! I was trying to run the FAIR benchmark using the validation and test set, but in both cases I get the following error: `Traceback (most...

Thanks @HavenFeng for this amazing work. Please suggest the steps required to test any custom image.

Thanks for the great work! I wonder how the ita value is predicted, which I could not find in the code.

Hello, I was trying to test the project with pictures other than the ones in the dataset, and so far I know that I need a cropped image with the...

Hello, once again thanks for the great project. I was playing with the outputs of TRUST in the generated npy file (texcode and lightcode), but I am a bit lost...

Thank you for publishing this work. You mention in the paper that more details are provided in the Supplementary. Is it available?

Thanks for this great work. I want to know how to train it on my own dataset.

I have tried to implement this repo on test dataset, but all the output images are same for each test image. Is anyone also facing same issue ?