tensorflow / tensorflow/graphics

Adding preprocessing functions for pointclouds

Open
#685 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.8k
Forks
374
PR merge metrics
No merged PRs in 30d

Description

Hello,

I have implemented various preprocessing functions in tensorflow, compatible with tf.data.Dataset API for augmenting pointclouds including jitter, random_cutout, random_translation, random_rotation, random_zoom, etc..

I was curious to know if they would fall in the scope of tfg so I could submit a PR.

These could be implemented as augmentation layers just like keras-cv augmentations. I am not sure if these fall into the scope of tfg or keras-cv

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 proposes point-cloud preprocessing functions such as jitter, random cutout, translation, rotation, and zoom, but names no files or tests. First clarify whether these augmentations belong in TensorFlow Graphics or Keras-CV and define the accepted scope. Done means an agreed implementation scope and contribution path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.