Splat To Mesh

Splat To Mesh

Packages a splat-to-mesh converter as a Docker app, by the name of its code, for turning gaussian splat scenes into 3D meshes. It suits 3D developers who want to run or read the converter.

Made by dylanebert on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Splat To Mesh is a Docker app on port 7860 whose name says it turns a splat into a mesh. The Space has no README text beyond its settings, so the details come from its files. These include app.py, a convert.py script, a core folder and a data_test folder, 20 files in all.

Who it suits: It suits 3D developers and creators who work with gaussian splats and want to see or run a converter, and anyone curious how such a conversion is organized.

Industry | Who uses it | How they use it | Example
Scanning | Creators of splat scans | Run the splat-to-mesh Docker app on a scan of their own | A creator starts the Docker image and gives it a splat file.
Software | Developers | Read the conversion code in convert.py and the core folder | A developer follows convert.py to see how a splat is processed.
Graphics research | Students | Test a conversion pipeline with the sample data folder | A student runs the app with the files in data_test.

If you need a documented converter with known settings, skip it, because the Space has no usage notes.

Where to use it:

• A web browser, through the Space's page on Hugging Face
• A local copy on Windows, macOS or Linux, using Docker

Use case | Who | What they get back
Convert online | Anyone with a splat | The result of the converter running in the Space
Run it locally | Developers | The same app from a Docker image on your own computer
Read the code | Learners | convert.py and the core folder

How to set it up:

• Docker on Windows, macOS or Linux, for a local copy
• Python and pip, for the download step

1. Install the huggingface_hub package.
2. Download the Space into a local folder named splat-to-mesh.
3. Move into that folder.
4. Build the Docker image.
5. Run the image and map port 7860.

pip install -U huggingface_hub
hf download dylanebert/splat-to-mesh --repo-type space --local-dir splat-to-mesh
cd splat-to-mesh
docker build -t splat-to-mesh .
docker run -it -p 7860:7860 splat-to-mesh

How to use it: Open the Space's page online. For a local copy, run the two Docker commands above and open port 7860 on your computer in a web browser.

Tool | What it does
app.py | The main file, which serves the app
convert.py | A script whose name points to the conversion step
core | A folder that, going by its name, holds the shared code
data_test | A folder that, going by its name, holds test data

Example: You build the image and start it with the run command. Then you open port 7860 in your browser, and the converter's page loads from your own computer.

For newcomers and experts: If you are new, a mesh is a 3D shape made from triangles, and a splat is a scene made of soft points. This app is meant to go from the second to the first.

If you know the field, the source gives no method details, such as the algorithm or the file formats. Read convert.py before you trust the output for real work.

Start the Docker app
Open port 7860 in a browser
Give it a splat
Get a mesh back

Good to know:

• The Space has no usage notes, so formats and settings are not documented
• The input and output formats are not named in the source
• License: mit
• Cost to run: none named
• Data it reaches: the files you give the app, and its own folders

On Hugging Face, 13 November 2026

• Likes: 36
• Built with: docker
• License: mit

Links

• Space: https://huggingface.co/spaces/dylanebert/splat-to-mesh
• Files: https://huggingface.co/spaces/dylanebert/splat-to-mesh/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.