How to use 4DNex-10M dataset
Open
- Dominant language
- Python
- Stars
- 840
- Forks
- 14
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I noticed that the depth maps in the 4DNeX-10M dataset have a resolution of 28×288×512. Does this mean the original images are first resized to 288×512, and then depth and camera pose are predicted at this resolution?
I also observed that some open-source implementations use a resolution of 81×480×720 instead. Could you explain the reason for this discrepancy? Is it due to different preprocessing settings or evaluation protocols?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.