Unity-Technologies / Unity-Technologies/sentis-samples

Help with implementing YOLO3D inference in Unity (Sentis)

Open
#27 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C#
Stars
358
Forks
73
PR merge metrics
No merged PRs in 30d

Description

Hi,

I’m porting the YOLO3D (YOLOv5 + Regression model) inference from yolo3d-lightning/inference.py
to Unity using Sentis.

The Python code relies on utility functions from Python: src.utils.Math:

  • calc_location
  • compute_orientation
  • recover_angle
  • translation_constraints

and KITTIObject from src.utils.utils.

I’ve attempted a C# implementation, but the rotations are coming out incorrect.

I’m looking for guidance or references on translating such a script to C# / Unity, particularly for handling camera-space transforms and orientation recovery correctly.

Thanks!

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

Start by comparing yolo3d-lightning/inference.py with the listed src.utils.Math functions and KITTIObject in src.utils.utils. Review the existing attempted C# implementation referenced in the issue, focusing on camera-space transforms and orientation recovery. Done would be a clearly documented Unity Sentis translation approach or a working implementation with correct rotations.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp, unity
Domain
computer-vision, machine-learning
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.