Image-to-3D
ONNX
Depth Pro
onnxruntime
gaussian-splatting
monocular-view-synthesis
novel-view-synthesis
sharp
oku3d
fp16
opset21
stereo
Instructions to use Jens-Duttke/Sharp-ONNX-HighPerf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Depth Pro
How to use Jens-Duttke/Sharp-ONNX-HighPerf with Depth Pro:
# Download checkpoint pip install huggingface-hub huggingface-cli download --local-dir checkpoints Jens-Duttke/Sharp-ONNX-HighPerf
import depth_pro # Load model and preprocessing transform model, transform = depth_pro.create_model_and_transforms() model.eval() # Load and preprocess an image. image, _, f_px = depth_pro.load_rgb("example.png") image = transform(image) # Run inference. prediction = model.infer(image, f_px=f_px) # Results: 1. Depth in meters depth = prediction["depth"] # Results: 2. Focal length in pixels focallength_px = prediction["focallength_px"] - Notebooks
- Google Colab
- Kaggle

- Xet hash:
- 0a569c3471ecd1035fb075977dcd5dfa127e6f08e4ffb4148b411741e2a1e489
- Size of remote file:
- 2.56 MB
- SHA256:
- 6c9d8581a54725621a321cd47a6bc9d8ac35f0371ee7f8dbb1fdbeb83789fb3b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.