compphoto/BoostingMonocularDepth

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1507 stars · 202 forks observed · 2026-08-28

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

A Python research implementation for boosting monocular depth estimation to high resolution using a double-estimation merging operator, supporting MiDaS and LeRes depth networks. It produces high-resolution depth maps from single RGB images and includes a related scale-invariant depth estimation follow-up (SI-depth, SIGGRAPH 2024).

Use cases

• generate high-resolution depth maps from single photos
• boost MiDaS or LeRes depth estimates to higher resolution
• estimate depth from a single RGB image
• merge low-res and high-res monocular depth predictions
• research on monocular depth estimation networks
• create depth maps for 3D projection from images

When to choose

• you need high-resolution depth maps from single images
• you want to apply the double-estimation merging operator to MiDaS or LeRes outputs
• you are doing computer vision research on monocular depth estimation

When to avoid

• you need real-time depth estimation on edge devices
• you want a production-ready supported product with a clear license
• you need a maintained library with active development

Facets

library · maturity maintenance

machine-learning computer-vision image-processing computer-vision machine-learning image-processing deep-learning python windows monocular-depth-estimation depth-maps high-resolution research-code midas leres siggraph linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="compphoto/BoostingMonocularDepth")