# megvii-research/PETR

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images

Repository: https://github.com/megvii-research/PETR
Canonical: https://ross.abutalabs.com/products/petr
Language: Python
License: NOASSERTION
License Family: other
Topics: multi-camera, multi-task-learning, object-detection, segmentation, 3d-position-embedding
Last push: 2023-10-11T05:59:40+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1549, "days_push": 1057, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1065, forks 160 (observed 2026-08-28T04:03:26.743912+00:00)

## What it is
Official PyTorch implementation of PETR and PETRv2, transformer-based frameworks for multi-view 3D object detection and BEV segmentation from multi-camera images using 3D position embedding transformation. It serves as a strong research baseline for camera-only 3D perception, achieving state-of-the-art results on nuScenes.

## Use cases
- multi-view 3d object detection from camera images
- bev segmentation from multi-camera setup
- research baseline for camera-only 3d perception
- temporal modeling for 3d detection
- 3d lane detection experiments
- reproduce nuscenes benchmark results

## When to choose
- you need a proven camera-only 3D detection baseline for research
- you want state-of-the-art multi-camera detection or BEV segmentation on nuScenes
- you are building on position-embedding-based 3D perception methods

## When to avoid
- you need a production-ready perception stack for a deployed vehicle
- you require a permissive license (license is non-standard)
- you need active feature development rather than a research artifact

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision
- domain: computer-vision, autonomous-vehicles, deep-learning, artificial-intelligence
- platform: python
- tags: 3d-object-detection, multi-camera, position-embedding, bev-segmentation, nuscenes, research-code, transformer-detection, linux, gpu

## Member repositories
- megvii-research/PETR (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:26.743912+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 2026-08-30T06:55:30.486068+00:00, confidence not recorded.
  - readme: https://github.com/megvii-research/PETR (fetched 2026-08-28T04:03:26.743912+00:00, sha 303aead9dca7)
- Data as of 2026-08-30T08:39:29.467469+00:00.