search

HarshayuGirase / Human-Path-Prediction

State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.
MIT License
348 stars 81 forks source link

Homographic Matrix for UCY used in Y-Net #27

Closed HRHLALALA closed 3 years ago

HRHLALALA commented 3 years ago

Hi, I am building the dataset for UCY and ETH dataset. To conduct a fair experiment, can you provide the homographic matrix used for UCY? Also, do you use same scene images among uni_examples and UNIV (student00) as well as among Zara datasets? Thanks.

karttikeya commented 3 years ago

Hi, thanks for your interest in our work. Here are the homography matrices:

https://drive.google.com/drive/folders/1ycxLUluANUXSHNmJQ8w4Nx8nVQXiB2F3.

For univ, we use the same scene images but for zara1,2 there is a very slight difference between the reference images.

sff1019 commented 2 years ago

@HRHLALALA Hi, I was wondering if you got similar results as the paper for Y-Net on ETH and UCY dataset. Thanks.

HRHLALALA commented 2 years ago

@HRHLALALA Hi, I was wondering if you got similar results as the paper for Y-Net on ETH and UCY dataset. Thanks.

I am currently using the dataset from Social GAN to train but unfortunately not yet got the results. I will let you know when the results come out.

sff1019 commented 2 years ago

Thanks for the quick response! I see, FYI I've trained a new model using the dataset from Social GAN and for the ETH split I've got 

ADE: 0.58 (paper: 0.28)
FDE: 0.84 (paper: 0.33)

This is unfortunately very different from the original numbers in the paper. It would be great if you can check it with yours once you have it. Thanks.

Kay1794 commented 2 years ago

Thanks for the quick response! I see, FYI I've trained a new model using the dataset from Social GAN and for the ETH split I've got

ADE: 0.58 (paper: 0.28)
FDE: 0.84 (paper: 0.33)

This is unfortunately very different from the original numbers in the paper. It would be great if you can check it with yours once you have it. Thanks.

Hi @sff1019, I know it may be a little bit outdated, but I am wondering if you have achieved similar numbers on the Social GAN split for the ETH dataset? Any comments would be highly appreciated!

SunshineDHW commented 8 months ago

Thanks for the quick response! I see, FYI I've trained a new model using the dataset from Social GAN and for the ETH split I've got

ADE: 0.58 (paper: 0.28)
FDE: 0.84 (paper: 0.33)

This is unfortunately very different from the original numbers in the paper. It would be great if you can check it with yours once you have it. Thanks.

Hi: @sff1019,Could you tell me How to implement YNet?What changes have you made based on SDD? Thank you for you help1