Many floating artifacts in image
- Dominant language
- Jupyter Notebook
- Stars
- 2.8k
- Forks
- 458
- PR merge metrics
- No merged PRs in 30d
Description
I'm getting many floating artifacts in my scenes. From what I've heard in [this talk](https://youtu.be/HfJpQCBTqZs?t=1653), it might be due to L set too high. From your experience, is this really the cause? Would this be solved if gaussian embeddings were used, or SIREN activations? From what I've seen in [this thread](https://github.com/bmild/nerf/issues/60), you've tried these approaches already.
https://user-images.githubusercontent.com/1536515/133931076-bb6a880e-e5e0-422a-984b-1f0ef61c8ec6.mp4
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no file, test, or entry point. Start by reproducing the attached scene and tracing the rendering path to determine whether the reported artifacts correlate with L, Gaussian embeddings, or SIREN activations. Done would require a confirmed cause and a reproducible resolution or documented limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch
- Domain
- computer-graphics, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100