example of piping grounding-segment-anything with ZoeDepth estimation
in your venv
python -m pip install -e .
create folder 'testinput' and 'weights', adding image and models(groundingdino_swint_ogc.pth, sam_vit_h_4b8939.pth,ZoeD_M12NK.pt) then the running the 'segdepth.py' shall showing the masked segmentation with annoattion of confidence level, name and depth( depth in this example is calculated by average of the depth map pixels in the masked region)
| Title | Intro | Description | Links |
|---|---|---|---|
| Segment-Anything |  |
A strong foundation model aims to segment everything in an image, which needs prompts (as boxes/points/text) to generate masks | Github Page Demo |
| Grounding DINO |  |
A strong zero-shot detector which is capable of generating high-quality boxes and labels with free-form text. | Github Demo |
| ZoeDepth |  |
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth | Demo |
| MiDas | Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer | - |