Carton

QuickstartDocsModels

intel / dpt-hybrid-midas

DPT hybrid is a monocular depth estimation model

Examples

Inputs

Name: image

Outputs

Name: depth

Self tests

quickstart

Inputs

Name: image

Outputs

Usage

Inputs

Name: image

Description: The input image as an NHWC tensor

Type: uint8

Shape: [batch_size, height, width, num_channels]

Outputs

Name: depth

Description: The estimated depth map as an NHW tensor

Type: uint8

Shape: [batch_size, height, width]

Readme

DPT-Hybrid is model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper Vision Transformers for Dense Prediction by Ranftl et al. (2021). DPT uses the Vision Transformer (ViT) as backbone and adds a neck + head on top for monocular depth estimation.

Get it

Copy the model URL:

https://carton.pub/intel/dpt-hybrid-midas/d5ba6aa9073bbdf6831ad916c45992ab1c7e7a318531cd05ca48ad8ec7616847
This model has quickstart code available for every supported language.

Homepage

https://huggingface.co/Intel/dpt-hybrid-midas

License

Apache-2.0

Tasks

cv/depth-estimation