# chaytonmin/Awesome-BEV-Perception-Multi-Cameras

Awesome papers about Multi-Camera 3D Object Detection and Segmentation in Bird's-Eye-View, such as DETR3D, BEVDet, BEVFormer, BEVDepth, UniAD

Repository: https://github.com/chaytonmin/Awesome-BEV-Perception-Multi-Cameras
Canonical: https://ross.abutalabs.com/products/awesome-bev-perception-multi-cameras
License Family: other
Last push: 2024-04-26T09:14:39+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": 1592, "days_push": 859, "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 1114, forks 115 (observed 2026-08-28T04:03:38.275140+00:00)

## What it is
A curated awesome-list of research papers on multi-camera bird's-eye-view (BEV) 3D perception, covering 3D object detection and segmentation methods like DETR3D, BEVFormer, BEVDet, and UniAD. Each entry links to the paper and its official GitHub implementation, organized by publication venue and year.

## Use cases
- find papers on multi-camera 3D object detection
- survey bird's-eye-view perception methods for autonomous driving
- compare BEVFormer BEVDet and DETR3D implementations
- research vision-centric 3D perception from surround cameras
- find state-of-the-art BEV segmentation papers
- get started with camera-based 3D detection for self-driving

## When to choose
- you need a curated reading list of BEV perception research with links to code
- you are surveying multi-camera 3D detection and segmentation literature
- you want to track the evolution of BEV methods from LSS to UniAD

## When to avoid
- you need runnable software rather than a paper index
- you need LiDAR-based or single-camera-only 3D detection resources
- you expect maintained code, releases, or support - this is a link collection

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: autonomous-vehicles, computer-vision, artificial-intelligence, awesome-lists
- platform: cross-platform
- tags: awesome-list, bev-perception, 3d-object-detection, multi-camera, autonomous-driving, paper-collection, bird-eye-view

## Member repositories
- chaytonmin/Awesome-BEV-Perception-Multi-Cameras (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.275140+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 2026-08-30T06:42:16.440820+00:00, confidence not recorded.
  - readme: https://github.com/chaytonmin/Awesome-BEV-Perception-Multi-Cameras (fetched 2026-08-28T04:03:38.275140+00:00, sha 83f7a4833df7)
- Data as of 2026-08-30T08:39:29.467469+00:00.