microsoft / microsoft/TRELLIS.2
Why is the range of dual_vertices [-0.5, 1.5] rather than [0, 1]?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.3k
- Forks
- 1.4k
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/microsoft/TRELLIS.2/blob/903bfcf51af09b3fc6c408d2c7f2335febab7f81/trellis2/models/sc_vaes/fdg_vae.py#L100
This is a bit confusing to me. Considering that the calculation of mesh_vertices is as follows:
https://github.com/microsoft/TRELLIS.2/blob/903bfcf51af09b3fc6c408d2c7f2335febab7f81/o-voxel/o_voxel/convert/flexible_dual_grid.py#L268
According to the o-voxel encoding (dual_vertices = dual_vertices * RES - voxel_indices), intuitively dual_vertices should lie in [0, 1]. Could it be that in practice dual_vertices exceed [0, 1], landing in half of a neighboring voxel?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Read trellis2/models/sc_vaes/fdg_vae.py around line 100 and o-voxel/o_voxel/convert/flexible_dual_grid.py around line 268. Trace the dual_vertices encoding and mesh_vertices calculation to determine whether values outside [0, 1] are expected. Done means providing a clear explanation of the [-0.5, 1.5] range and documenting the relevant behavior if needed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-graphics
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100