prs-eth/PaGeR-depth-indoor

📟 PaGeR(Panoramic Geometry Estimation) Depth Estimation Model Card

This is a model card for the PaGeR-depth-indoor model for monocular depth estimation from a single panoramic ERP image. The model is fine-tuned from our original depth checkpoint on the combination of Scannet and Structured3D datasets, specialized for indoor depth prediction, as described in our paper:

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

This model excels in depth estimation for indoor environments, for a more general model, check out the original model. You can also check out other depth and normals models in our collection, 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 scale-invariant 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.
  • Dataset: Scannet++, Structured3D
  • Steps and scheduler: This model works in a swift, one-step regime.
  • Outputs:
    • Scale-invariant depth map: The predicted values represent a depth map, interpolating between the near and far planes of the model's choice.
• Resources for more information: [Project Website](insert link), [Paper](insert link), Code.
• Cite as:

Add citation