prs-eth/PaGeR-metric-depth

📟 PaGeR(Panoramic Geometry Estimation) Depth Estimation Model Card

This is a model card for the PaGeR-metric-depth model for metric monocular depth estimation from a single panoramic ERP image. The model is fine-tuned from the marigold-e2e-ft model as described in our paper:

• [Paper](paper link) titled "Panorama Geometry Estimation using Single-Step Diffusion Models"

You can also check out our scale-invariant depth estimation model, surface normals estimation model, or test models in our demo.

Model Details

• Developed by: Vukasin Bozic, Isidora Slavkovic, Dominik Narnhofer, Nando Metzger, Denis Rozumny, Konrad Schindler, Nikolai Kalischek.
• Model type: Generative latent diffusion-based one-step metric monocular panoramic depth estimation from a single ERP image.
• License: CreativeML OpenRAIL License.
• Model Description: This model can be used to generate an estimated depth map of a panoramic input image.
  • Resolution: The model is designed to support large resolutions up to 3K.
  • Steps and scheduler: This model works in a swift, one-step regime.
  • Outputs:
    • Metric depth map: The predicted values represent a depth map, interpolating between the near and far planes of the model's choice, in meters.
• Resources for more information: [Project Website](insert link), [Paper](insert link), Code.
• Cite as:

Add citation