microsoft / microsoft/MoGe

Estimation for extrinsic camera parameters

Open
#99 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
JavaScript
Stars
3k
Forks
234
PR merge metrics
No merged PRs in 30d

Description

Hello MoGe team,

Thanks for such great work. In the GitHub repo, you mention that MoGe can recover intrinsic camera parameters. I wonder if it can also estimate extrinsic camera parameters. In the supp. According to the material of the MoGev1 paper, you mentioned that you assume a simple pinhole camera model with an isotropic focal length and a centered principal point to predict the intrinsic parameters. Since MoGev2 is more accurate than MoGev1, is it possible to extract the external camera parameters from MoGev2? Or are the point maps from the camera perspective instead of world coordinates?

Also, what are the affine-invariant point maps? Could you provide a reference about that topic?

Regards,
Sebastian

Contributor guide

No contributing guide indexed for this repository

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

The issue names no files, tests, or entry points; start by reviewing the MoGe v1 and MoGe v2 material referenced in the question. Done means clarifying whether extrinsic parameters are exposed, how point maps are referenced, and providing a reference for affine-invariant point maps.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.