Project AURIONAI Use-Cases Research & Innovation
Nanjing University
driving

BEVFormer

Bird's-eye-view perception from multiple cameras with spatiotemporal transformers, for 3D detection and map segmentation in autonomous driving.

Nanjing UniversityNanjing UniversityChinaShanghai AI LabShanghai AI LabChina
Overall architecture of BEVFormer with temporal and spatial cross-attention on bird's-eye-view queries, from the BEVFormer README.
Levelmodel
Classdriving
Parametersnot in the notes
Contextnot in the notes
Released31 Mar 2022
Opennessopen source
Runs onmobile or NPU
Statusactive

R&D Topics

Multi-camera bird's-eye-view 3D perceptionexemplar

Identity

Developer
Nanjing University, Shanghai AI Lab
Family
not in the notes
Released
31 Mar 2022 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image, sensor
Output
3D
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open source
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, TI edge AI model zoo.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2203.17270 https://arxiv.org/abs/2203.17270
  2. github.com/fundamentalvision/BEVFormer https://github.com/fundamentalvision/BEVFormer
  3. aihub.qualcomm.com/models/bevformer https://aihub.qualcomm.com/models/bevformer
  4. github.com/fundamentalvision/BEVFormer https://github.com/fundamentalvision/BEVFormer/
  5. github.com/TexasInstruments/edgeai-tensorlab/tree/main/e... https://github.com/TexasInstruments/edgeai-tensorlab/tree/main/edgeai-modelzoo/models/vision/detection_3d/pandaset
  6. arxiv.org/html/2203.17270 https://arxiv.org/html/2203.17270

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BEVFormer", https://aurion.semai.id/models/bevformer/, records of October 2026.