facebookresearch / facebookresearch/co-tracker
question about backward_tracking
- Dominant language
- Jupyter Notebook
- Stars
- 5.1k
- Forks
- 389
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/16lemoing/dot/blob/e32c6f7de12342460371f2efc4789bd79c4a39a3/dot/models/shelf/cotracker2_utils/predictor.py#L145-L153
Hi, I am a bit confused about backward_tracking. First, back_tracking means computing the trajectory starting from the last frame to the first N-1 frames? If so, does backward_tracking benefit (get higher accuracy) from forward_tracking? And do the variables "tracks and visibilities" in L153 overwrite those in L145? Thanks!
Contributor guide
Research direction
Read dot/models/shelf/cotracker2_utils/predictor.py around lines 145-153 and trace the backward_tracking path. Compare how tracks and visibilities are produced in the forward and backward passes, then document whether backward tracking starts from the last frame, uses forward results, or overwrites them.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100