How to use a Gaussian related loss function to replace the original one?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.7k
- Forks
- 1.3k
- PR merge metrics
- No merged PRs in 30d
Description
Since the compute loss function only include the （ x_0: sp.SparseTensor, cond=None, ），how can we decode them into a gaussian version so that some loss function which need the position, rotation, scale, opacities, features_dc can be used ?
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
Start by tracing the compute loss function and its x_0: sp.SparseTensor, cond=None inputs. Determine whether they can expose the Gaussian properties named in the issue—position, rotation, scale, opacities, and features_dc—and define the expected loss integration and decoding behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-graphics, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100