360 rendering result is bad
- Dominant language
- Jupyter Notebook
- Stars
- 2.8k
- Forks
- 458
- PR merge metrics
- No merged PRs in 30d
Description
my traning tensor-board result looks nice.
But, when eval the result is no so good. I don't known what's going wrong.
I want to known, my dataset is reasonable? Nerf is suitable for my dataset？
colmap gui result as following:
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by comparing the TensorBoard training result with the evaluation result and reviewing the dataset and COLMAP GUI output shown in the issue. Done would require determining whether the dataset is suitable for NeRF and explaining or correcting the evaluation quality gap.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100