search

tarashakhurana / 4d-occ-forecasting

CVPR 2023: Official code for `Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting'
https://www.cs.cmu.edu/~tkhurana/ff4d/index.html
MIT License
215 stars 23 forks source link

About the input occupancy #12

Closed placeforyiming closed 10 months ago

placeforyiming commented 10 months ago

Hi, thanks for sharing the code

A quick question:

What is the exactly used method to transform the input point clouds to occupancy voxels as the network input?

From the implementation, if a voxel has at least one point inside of it, then the voxel is marked as 1. So no ray-casting is used here. However, the comment here https://github.com/tarashakhurana/4d-occ-forecasting/blob/ff986082cd6ea10e67ab7839bf0e654736b3f4e2/model.py#L240 says the ray-casting is used and the space status is triple instead of binary.

tarashakhurana commented 10 months ago

Hi, thanks for the question! Unfortunately, the comment in the code is misleading and the input occupancy is binary. This is also explained in the paper in Section 3.

placeforyiming commented 10 months ago

Hi, thanks for the question! Unfortunately, the comment in the code is misleading and the input occupancy is binary. This is also explained in the paper in Section 3.

Got it! Thanks for the quick reply