CompVis / CompVis/EDGS

What is the EDGS initialization method different from adopting a dense point cloud using the MVS method directly?

Open
#10 3 comments 6 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
742
Forks
59
PR merge metrics
No merged PRs in 30d

Description

Thanks to the author for his excellent work! There is related work doing 3DGS initialization using dense point clouds generated by the MVS method, and your approach uses Roma feature matching and triangulation to reconstruct denser point clouds by sampling portions of all images.

I was wondering if there is any difference between your method and using MVS initialization?
Is it an improvement in efficiency or is the reconstructed point cloud in 3D space of higher quality?

How long does it take to reconstruct a dense point cloud using your method?

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 does not name files, tests, or entry points. Start by comparing EDGS's Roma feature-matching and triangulation initialization with dense point clouds produced by MVS, then examine reconstruction time and point-cloud quality against direct MVS initialization. Done means documenting the differences and reporting the relevant timing or quality observations.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, pytorch
Domain
computer-vision
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.