dimensionalOS / dimensionalOS/dimos

PimSim: Unreal-to-splat and cooked-physics pipeline

Open
#3,336 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.5k
Forks
808
Avg merge
3d 5h
Merged PRs (30d)
233

Description

Turn one versioned Unreal-class scene into aligned camera and physical worlds.

Acceptance

  • Preserve asset hierarchy, IDs, transforms, materials, and available semantics
  • Export deterministic RGB, masks, depth, intrinsics, and extrinsics
  • Run COLMAP mapping, densification, and splat training with retained provenance
  • Cook source geometry independently into collision, navigation, and MuJoCo assets
  • Measure alignment and run ordinary DimOS camera and navigation workflows

Synced from DIM-1383 by pim

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

The issue names no files, tests, or entry points. Start by locating the existing scene, camera, navigation, and asset-export workflows, then determine how COLMAP, splat training, collision, navigation, and MuJoCo outputs fit together. Done means meeting every listed acceptance item, including provenance, alignment measurements, and ordinary camera and navigation workflows.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, unreal-engine
Domain
computer-graphics, computer-vision, robotics
Issue type
Feature
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.