search

Tsinghua-MARS-Lab / M2I

M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.
https://tsinghua-mars-lab.github.io/M2I/
MIT License
187 stars 24 forks source link

About interpolating missing trajectories #5

Closed daeunni closed 1 year ago

daeunni commented 2 years ago

@larksq Hi, thank you for your nice work! btw, in WOMD there are some missing trajectories(incomplete trajectories).

how did you handle this? did you interpolate missing points or just drop this whole trajectories?

Best,

larksq commented 1 year ago

I am glad that you like our work.

Dealing with incomplete trajectories is a common issue for the trajectory prediction task. We did not interpolate any missing points. Instead, we mask out these points during training and leave them as they are during predicting.

Best,