---
license: other
license_name: apple-amlr
license_link: LICENSE
tags:
  - gaussian-splatting
  - 3d-reconstruction
  - onnx
  - tortuise
pipeline_tag: image-to-3d
---

# SHARP ONNX — Apple's Single-Image 3D Gaussian Splatting

ONNX export of [Apple's SHARP model](https://github.com/apple/ml-sharp) for use with [tortuise](https://github.com/buildoak/tortuise), a terminal-native 3D Gaussian Splatting viewer.

## Files

| File | Size | Description |
|------|------|-------------|
| `sharp.onnx` | 1.9 MB | Model structure (ONNX graph) |
| `sharp.onnx.data` | 2.6 GB | Model weights (external data) |

Both files are required. The model exceeds protobuf's 2GB limit, so weights are stored separately.

## Usage

These files are automatically downloaded by tortuise when you run:

```bash
cargo install tortuise --features sharp
tortuise photo.jpg
```

Or manually place both files in `~/.tortuise/models/`.

## Model Details

- **Architecture:** DINOv2 ViT-Large encoder + Sliding Pyramid Network + DPT decoders
- **Parameters:** 702M (340M trainable)
- **Input:** Single RGB image (resized to 1536×1536 internally)
- **Output:** ~1.2M 3D Gaussians (positions, scales, rotations, colors, opacities)
- **ONNX opset:** 17
- **Source checkpoint:** `sharp_2572gikvuh.pt` from [apple/Sharp](https://huggingface.co/apple/Sharp)

## License

The model weights are licensed under the [Apple Machine Learning Research Model License](LICENSE). This is a **research-only, non-commercial** license. See the LICENSE file for full terms.

This ONNX conversion is a format transformation of Apple's original PyTorch checkpoint. No architectural modifications were made.

## Attribution

Based on Apple SHARP model. Copyright (C) 2025 Apple Inc. Licensed under the Apple Machine Learning Research Model License Agreement.

Paper: [SHARP: Monocular View Synthesis in Less Than a Second](https://arxiv.org/abs/2512.10685)