Nikhila Ravi d07307a451 Non square image rasterization for meshes ...

Summary:
There are a couple of options for supporting non square images:
1) NDC stays at [-1, 1] in both directions with the distance calculations all modified by (W/H). There are a lot of distance based calculations (e.g. triangle areas for barycentric coordinates etc) so this requires changes in many places.
2) NDC is scaled by (W/H) so the smallest side has [-1, 1]. In this case none of the distance calculations need to be updated and only the pixel to NDC calculation needs to be modified.

I decided to go with option 2 after trying option 1!

API Changes:
- Image size can now be specified optionally as a tuple

TODO:
- add a benchmark test for the non square case.

Reviewed By: jcjohnson

Differential Revision: D24404975

fbshipit-source-id: 545efb67c822d748ec35999b35762bce58db2cf4

2020-12-09 09:18:11 -08:00

..

assets

examples and docs.

2020-11-03 13:06:35 -08:00

batching.md

Setup website with docusaurus (#11)

2020-02-04 17:27:16 -08:00

cameras.md

small website updates

2020-08-26 09:21:43 -07:00

cubify.md

small website updates

2020-08-26 09:21:43 -07:00

datasets.md

small website updates

2020-08-26 09:21:43 -07:00

meshes_io.md

Single function to load meshes from OBJs. join_meshes.

2020-02-13 03:38:07 -08:00

renderer_getting_started.md

Non square image rasterization for meshes

2020-12-09 09:18:11 -08:00

renderer.md

examples and docs.

2020-11-03 13:06:35 -08:00

visualization.md

Rename visualization to vis

2020-10-06 15:55:05 -07:00

why_pytorch3d.md

Use a consistent case for PyTorch3D

2020-03-17 12:48:43 -07:00