Getting the foreground mask from each pixel #33

New Issue

2023-09-16T23:10:44+08:00

Gynjn commented

2023-09-16 23:10:44 +08:00

(Migrated from github.com)

First, Thanks for your great work!

In paper page 4, "the M() is the foreground mask acquired by integrating the volume density along the ray of each pixel.", How could calulate the density in pixel?

For example, the naive NeRF gets density (sigma) from 3d coord query. Then just add them in all samples in ray and normalize?

Thanks.

First, Thanks for your great work! In paper page 4, "the M() is the foreground mask acquired by integrating the volume density along the ray of each pixel.", How could calulate the density in pixel? For example, the naive NeRF gets density (sigma) from 3d coord query. Then just add them in all samples in ray and normalize? Thanks.

guochengqian commented

2023-10-13 16:47:03 +08:00

(Migrated from github.com)

7f051875e4/nerf/renderer.py (L1073)

https://github.com/guochengqian/Magic123/blob/7f051875e48988dc624b2bd8425aea370c093588/nerf/renderer.py#L1073

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: dearsky/Magic123#33