Question about the multimodel end point sampling

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

349 stars 81 forks source link

Question about the multimodel end point sampling #20

Closed JiajianLu closed 2 years ago

JiajianLu commented 3 years ago

Hi, thank you for providing the code. I'm just wondering how do you sample the multimodel end points from only one Gaussian distribution? Should it be GMM instead?

ArcaneEmergence commented 2 years ago

The end point distribution are not Gaussian. They are non-parameterized, i.e., each pixel has a probability value. For goals we use TTST to sample (see paper) and for trajectory points, we use softargmax.