microsoft / microsoft/DAViD

Point cloud from depth

Open
#24 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
397
Forks
34
PR merge metrics
No merged PRs in 30d

Description

Hey! Thanks for this amazing work!

How can I get 3D point cloud from depth?
I know intrinsics of a camera and when I project pixels based on intrinsics and predicted depth(not inverse) I get a flat point cloud.
In your paper there is information how to get 2.5D point cloud, but this information isn't clear for me.
What does "reasonable guess of a range" phrase mean?
Thanks!

Image

Below some examples of generated 3D point cloud from samples of Nersemble Dataset.

Image Image

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 a source file, test, or implementation entry point. Start by reading the paper's 2.5D point-cloud section and the project's depth-processing documentation or examples, then determine whether the requested clarification belongs in the documentation. Done means explaining how predicted depth and camera intrinsics produce a 3D point cloud and clarifying the phrase "reasonable guess of a range."

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.