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:
- 8219d433f407b6f754d09c4bbf65103378c09b2b5c149bc5e855746054ef0d3d
- Size of remote file:
- 299 kB
- SHA256:
- 69ae6c2be6a376422708e1354bb7bf4b81a2b6d340822f0fe0fee987a35d8a85
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.