selmee/depth-pro

<h1 align="center">Web UI for Depth-Pro</h1>

<p align="center"> <img src="./example.jpg" alt="Web UI for Depth-Pro Depth Estimation" /> </p>

Metric depth estimation determines real-world distances to objects in a scene from images. This repo provides a web UI that allows users to estimate metric depth and visualize depth maps by easily uploading images using the Depth Pro model through a simple Gradio UI interface.

🛠️ Getting Started

📦 Installation

1. 1.Create and activate a virtual environment:

   conda create -n depth-pro -y python=3.9
   conda activate depth-pro

1. 1.Clone the depth-pro repository:

   git clone https://github.com/apple/ml-depth-pro.git
   cd ml-depth-pro
   pip install -e .

1. 1.Clone the web UI repository:

   git clone https://github.com/spacewalk01/depth-pro-webui.git
   cd depth-pro-webui
   pip install -r requirements.txt

1. 1.Download the model:

Download the model from depth_pro.pt and place the file in a newly created checkpoints folder.

🚀 Running the Application

1. 1.Launch the Gradio interface:

   python main.py

1. 1.Open the provided local URL in your web browser to access the interface.

🖼️ Usage

1. 1.Upload an Image: Use the image uploader to select an image for depth estimation.
2. 2.Adjust Options:
3. 3.Auto Rotate: Enable or disable auto-rotation of the image.
4. 4.Remove Alpha: Enable or disable the removal of the alpha channel.
5. 5.View Results:
6. 6.The depth map will be displayed on the interface.
7. 7.The focal length in pixels will also be shown.

📜 License

This project is licensed under the Apple License. See the LICENSE file for details.

🙏 Acknowledgments

• —Gradio for providing an easy interface for machine learning models.
• —Depth Pro for enabling sharp monocular metric depth estimation in less than a second.