NVIDIAGameWorks / NVIDIAGameWorks/kaolin
Running tutorial on different Omniverse kitchenset data- does not fit objects
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5.2k
- Forks
- 629
- Avg merge
- 53m
- Merged PRs (30d)
- 2
Description
Swapping out the clock files for a kitchenware set of images (10 images) generated by the Kaolin datagenerator in Omniverse, following the Kaolin video tutorial, results in mesh generation that is roughly stuck in the shape of a sphere. Examples for the 'ladle' mesh completely failed.
Shown here is the pot mask where the handle can't be learned:
Should the tutorial code be runnable on other data generated using the kitchenset files? I had thought it could overfit to a single mesh example but it's having issues with shapes. My understanding was that the sphere template wasn't a barrier for these kinds of deformations?
Contributor guide
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
Start by rerunning the Kaolin video tutorial with the described 10-image kitchenset input and compare it with the clock data. Inspect the tutorial's mesh-generation step and the pot and ladle masks; done means determining whether the failure is reproducible and documenting a concrete correction or limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-graphics, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100