# Robbyant/lingbot-depth

Masked Depth Modeling for Spatial Perception

Repository: https://github.com/Robbyant/lingbot-depth
Canonical: https://ross.abutalabs.com/products/lingbot-depth
Homepage: https://technology.robbyant.com/lingbot-depth
Language: Python
License: Apache-2.0
License Family: permissive
Topics: depth, depth-camera, masked-image-modeling
Last push: 2026-07-08T06:38:12+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 35, longevity 15
- inputs: {"age_days": 220, "days_push": 56, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1610, forks 118 (observed 2026-08-28T04:05:10.885040+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, robotics, machine-learning, autonomous-vehicles
- platform: python
- tags: depth-completion, depth-estimation, masked-image-modeling, spatial-perception, pytorch, robot-learning, 3d-vision, pretrained-models, gpu, linux

## Member repositories
- Robbyant/lingbot-depth (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.885040+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:51:13.524767+00:00, confidence not recorded.
  - readme: https://github.com/Robbyant/lingbot-depth (fetched 2026-08-28T04:05:10.885040+00:00, sha aa1a4c43c373)
  - homepage: https://technology.robbyant.com/lingbot-depth (fetched 2026-08-29T11:23:19.889717+00:00, sha 6857925e188d)
  - site_page: https://www.robbyant.com/about-robby (fetched 2026-08-29T11:23:20.104820+00:00, sha 4a2374d8a183)
- Data as of 2026-08-30T08:39:29.467469+00:00.