# mileyan/pseudo_lidar

(CVPR 2019) Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

Repository: https://github.com/mileyan/pseudo_lidar
Canonical: https://ross.abutalabs.com/products/pseudo_lidar
Homepage: https://mileyan.github.io/pseudo_lidar/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2020-07-02T16:17:23+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2798, "days_push": 2253, "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 1005, forks 216 (observed 2026-09-03T02:15:15.113230+00:00)

## What it is
Research code implementing Pseudo-LiDAR, a CVPR 2019 method that converts image-based depth maps into pseudo-LiDAR point clouds for 3D object detection in autonomous driving. It includes training scripts for stereo depth estimation and 3D detectors on the KITTI benchmark, plus point cloud visualization notebooks.

## Use cases
- detect 3D objects from stereo camera images
- convert depth maps to point clouds
- train 3D object detection on KITTI
- replicate pseudo-lidar paper results
- visualize lidar point clouds from depth estimation
- avoid expensive lidar sensors for autonomous driving perception

## When to choose
- you need image-based 3D object detection without LiDAR hardware
- you want to reproduce or build on the CVPR 2019 pseudo-lidar paper
- you're working with KITTI stereo depth estimation pipelines

## When to avoid
- you need a production-ready, actively maintained detection system
- you want a plug-and-play library with a stable API
- you need real-time detection on embedded hardware

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning, image-processing
- domain: autonomous-vehicles, computer-vision, deep-learning, machine-learning
- platform: python
- tags: 3d-object-detection, depth-estimation, lidar, kitti, stereo-vision, research-code, cvpr-2019, linux, gpu

## Member repositories
- mileyan/pseudo_lidar (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.113230+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 2026-08-30T07:13:10.557710+00:00, confidence not recorded.
  - readme: https://github.com/mileyan/pseudo_lidar (fetched 2026-09-03T02:15:15.113230+00:00, sha 9b201fd44495)
  - homepage: https://mileyan.github.io/pseudo_lidar/ (fetched 2026-08-29T13:13:14.795691+00:00, sha 637cd40ba927)
- Data as of 2026-08-30T08:39:29.467469+00:00.