Robbyant/lingbot-depth

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1610 stars · 118 forks observed · 2026-08-28

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

LingBot-Depth is a PyTorch-based model and toolkit for masked depth modeling that transforms incomplete, noisy depth sensor data into metric-accurate 3D measurements by jointly aligning RGB appearance and depth geometry. It provides pretrained models for depth completion, refinement, monocular depth estimation, and stereo matching, targeting robot learning and 3D vision applications.

Use cases

• complete missing depth regions from noisy depth camera data
• estimate metric-scale depth from a single RGB image
• reconstruct indoor scenes with a strong depth prior
• track 4D points in metric space for robot learning
• enable robotic grasping of transparent and reflective objects
• refine sparse raw depth from consumer depth sensors
• process temporally consistent depth sequences from video

When to choose

• you need metric-accurate depth completion or refinement for robotics or 3D vision
• your depth camera fails on glass, mirrors, or reflective surfaces
• you want state-of-the-art monocular depth estimation or stereo matching with pretrained weights
• you need temporally consistent depth for video inputs

When to avoid

• you need a lightweight CPU-only depth solution
• you only need RGB-only semantic segmentation or object detection
• you require a turnkey GUI application rather than a Python model library

Facets

library · maturity active

machine-learning deep-learning computer-vision image-processing computer-vision robotics machine-learning autonomous-vehicles python depth-completion depth-estimation masked-image-modeling spatial-perception pytorch robot-learning 3d-vision pretrained-models gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Robbyant/lingbot-depth")