mapillary / mapillary/OpenSfM

Covariance field empty

Open
#968 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.8k
Forks
899
PR merge metrics
No merged PRs in 30d

Description

Hello @fabianschenk : I'm just getting started with opensfm. When I checked my reconstruction.json, the covariance field was empty for the data/berlin. How can I enable covariance or get the computed covariance field explicitly?

Also, can you guide me on how I can check or deduce something like a confidence score over the feature descriptors, which feature descriptor is credential and which is not? Is there any utility within the API that I could use to get that?

Thanks in advance for your help.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing how reconstruction.json is generated for the data/berlin dataset and review the API documentation for covariance and feature descriptors. Determine whether covariance can be enabled or exposed and whether the API provides descriptor confidence information; document the relevant entry points and a verifiable way to obtain both results.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.