Inquiry for the new focal length determined for undistortion
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 502
- Forks
- 34
- PR merge metrics
- No merged PRs in 30d
Description
Hi team：
First, thank you for this excellent data work — the VITRA-1M pipeline is a valuable contribution, and the ego-video → hand-VLA processing is very well thought out.
I have a question about the undistortion step. For videos that require undistortion, I'm trying to understand how the new focal length in new_K is chosen. It seems:
- For the Ego-Exo4D data, it looks like a fixed value is used.
- For Ego4D, however, the new focal length does not appear to be a fixed value — it seems to vary per video.
Could you clarify how the new focal length is determined for the Ego4D and Ego-Exo4d?
Thanks in advance!
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 locating the undistortion pipeline and the code that constructs new_K for Ego4D and Ego-Exo4D videos. Trace how each dataset's replacement focal length is selected, then document whether it is fixed or video-dependent and what inputs determine it. Done means the focal-length behavior for both datasets is clearly explained.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100