Add Common Objects in 3D (CO3D)

## Adding a Dataset
- **Name:** *Common Objects in 3D (CO3D)*
- **Description:** *See blog post [here](https://ai.facebook.com/blog/common-objects-in-3d-dataset-for-3d-reconstruction)*
- **Paper:** *[link to paper](https://arxiv.org/abs/2109.00512)*
- **Data:** *[link to data](https://ai.facebook.com/datasets/co3d-downloads/)*
- **Motivation:** *excerpt from above blog post:*

> As the first data set of its kind, CO3D will aptly enable reconstruction of real-life 3D objects. Indeed, CO3D already provides training data to enable our NeRFormer to tackle the new-view synthesis (NVS) task. Here, photorealistic NVS is a major step on the path to fully immersive AR/VR effects, where objects can be virtually transported across different environments, which will allow connecting users by sharing or recollecting their experiences.
>
> Besides practical applications in AR/VR, we hope that the data set will become a standard testbed for the recent proliferation of methods (including NeRFormer, Implicit Differentiable Renderer, NeRF, and others) that reconstruct 3D scenes by means of an implicit shape model.
>

Instructions to add a new dataset can be found [here](https://github.com/huggingface/datasets/blob/master/ADD_NEW_DATASET.md).