isl-org/ZoeDepth

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

2839 stars · 276 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ZoeDepth is a PyTorch library implementing metric depth estimation from a single image, combining relative and metric depth approaches with pretrained models loadable via torch hub. It is the official implementation of the ZoeDepth paper and includes evaluation, training, and a Gradio demo.

Use cases

• estimate metric depth from a single image
• monocular depth estimation with pretrained models
• zero-shot depth estimation on new datasets
• predict depth maps for photos in python
• 3d scene understanding from one image
• evaluate depth estimation models on NYU Depth v2

When to choose

• you need absolute metric depth (not just relative) from a single RGB image
• you want a pretrained, easy-to-load torch hub model for depth estimation
• you need a research baseline for monocular depth estimation

When to avoid

• you need actively maintained software with bug fixes and updates - Intel has ceased development
• you only need relative depth and can use actively maintained alternatives like MiDaS or Depth Anything
• you need production support or commercial maintenance guarantees

Facets

library · maturity abandoned

machine-learning deep-learning computer-vision image-processing transformers computer-vision deep-learning machine-learning artificial-intelligence python cross-platform depth-estimation monocular-depth metric-depth pytorch pretrained-models zero-shot-transfer torch-hub 3d-reconstruction gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="isl-org/ZoeDepth")