ml-for-3d-course/main/en/unit3/introduction.md

# Introduction

## ML-friendly 3D

Let's take a step back and consider the generative 3D pipeline as a whole.

![3D Pipeline](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/ml-for-3d-course/3d-pipeline.png)

After multi-view diffusion comes ML-friendly 3D. This is some non-mesh representation of 3D that's easy for AI to handle.

In the current 3D research ecosystem, this can be a lot of things:

- **Gaussian Splatting**: Detailed in this unit
- **Triplanes**: Latest state-of-the-art. Learn more in this [Community Notebook](https://colab.research.google.com/github/FeMa42/OpenLRM/blob/main/Introduction_to_triplanes_colab.ipynb)
- **NeRFs**: Synthesize novel views with a neural network
- and more

This is all changing very rapidly. So, like in the case of multi-view diffusion, ML-friendly 3D can be treated like a black box, using [pre-trained models](https://huggingface.co/models?pipeline_tag=image-to-3d&sort=trending).

## Gaussian Splatting

In this unit, I'll be diving deeper into one of these: Gaussian Splatting.

The reason I'm diving deeper into this is that, unlike the other representations, splats can be [rendered in real-time](https://huggingface.co/spaces/dylanebert/4DGS-demo), making them suitable for end-to-end 3D applications where everything is AI-compatible.

Let's get started!