Depth Estimation
Diffusers
Safetensors
English
MarigoldDepthPipeline
depth estimation
image analysis
computer vision
in-the-wild
zero-shot
Instructions to use prs-eth/marigold-depth-v1-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prs-eth/marigold-depth-v1-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("prs-eth/marigold-depth-v1-1", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Absolute depth estimation
#1
by BenjaminTT - opened
Hello, thank you for developing this impressive model! I have a question regarding the depth estimation output:
The model generates an affine-invariant depth map with values normalized between 0 (near plane) and 1 (far plane). Is there a way to obtain absolute distance measurements in meters (or other real-world units) from the predicted depth map? For example:
Are there plans to support absolute depth estimation (e.g., through calibration or additional metadata)?
Thanks again for your work!
Hi there, you are correct that the current models do not predict metric units. That is a somewhat harder problem. Feel free to follow us to learn when we release something along those lines!
toshas changed discussion status to closed