# apple-sharp-torch Fast single-image to 3D Gaussian splat model generating photorealistic novel views in under one second. **Details** - Model name: `apple-sharp-torch` - Model source: [https://github.com/apple/ml-sharp](https://github.com/apple/ml-sharp) - Model author: Lars Mescheder, et al. - Model license: Apple Sample Code License - Model size: 2.62 GB - Exposes embeddings? no - Tags: `3d, gaussian-splatting, novel-view, torch, transformer` **Requirements** - Packages: `torch, torchvision` - CPU support - yes - GPU support - yes **Example usage** ```python import fiftyone as fo import fiftyone.zoo as foz dataset = foz.load_zoo_dataset( "coco-2017", split="validation", dataset_name=fo.get_default_dataset_name(), max_samples=50, shuffle=True, ) model = foz.load_zoo_model("apple-sharp-torch") dataset.apply_model(model, label_field="predictions") session = fo.launch_app(dataset) ```