# Processing the SFU Motion Capture Dataset

## BVH Approach

Download .bvh animation data from the [SFU website](https://mocap.cs.sfu.ca/).

Enable the BVH import plugin in Blender

File -> Import -> Motion Capture (.bvh)

Use the following import settings

<figure><img src="/files/eveWcltJuCm0is3RBgo2" alt=""><figcaption></figcaption></figure>

Autodesk MotionBuilder uses Z forward and Y up frame.

<figure><img src="/files/J2dFkkhBls8OzUueIiez" alt=""><figcaption></figcaption></figure>

The animations are all in 120 FPS

## FBX Approach

> <mark style="color:red;">**Warning:**</mark> This approach does NOT work, since the fbx does not contain the original T-pose data.

Download .fbx animation data from the [SFU website](https://mocap.cs.sfu.ca/).

The .fbx file cannot be imported into Blender due to version mismatch.

<figure><img src="/files/IbQLw6TT2yJF30qsLF9Q" alt=""><figcaption></figcaption></figure>

Therefore, we need to convert the version using Autodesk MotionBuilder.

In MotionBuilder, open the .fbx file

<figure><img src="/files/uI0fcQ3Kn39WDbdDtTJ0" alt=""><figcaption></figcaption></figure>

Use default options to open

<figure><img src="/files/IeiLosdmOj58ZQSbfJrH" alt=""><figcaption></figcaption></figure>

Drag through the timeline and verify that everything looks good

<figure><img src="/files/fwiHHQw8VuWx3ln7Lloi" alt=""><figcaption></figcaption></figure>

Click File -> Save As..., and overwrite the original .fbx file. Also use the default options to save.

Now the animation file should be able to be imported to Blender.

When importing to Blender, click the "Automatic Bone Orientation" option under "Armature" tab.

<figure><img src="/files/M9RKXUdZDBivEjKzR7Dp" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://tk233.gitbook.io/notes/ml-rl/processing-the-sfu-motion-capture-dataset.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.