Qualcomm® AI HubAI Hub

BEVFormer

Transform temporal multi‑view images into a unified bird's eye scene.

Bevformer is a SOTA model of interest to the Auto BU.

Not supported

This model is currently not supported on any Mobile chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets
Model RepositoryHugging FaceResearch Paper

Technical Details

Input preprocessing:Images must be ImageNet mean/std normalized before inference; the model does not normalize internally.
Input resolution:6 x 3 x 480 x 800
Model checkpoint:bevformer_tiny_deformable_optimized_exp_86_epoch_24.pth
Model size:120 MB
Number of parameters:27M

Applicable Scenarios

  • Object Detection

Supported Mobile Form Factors

  • Phone
  • Tablet

License

Model:APACHE-2.0

Supported Mobile Devices

  • Samsung Galaxy S21
  • Samsung Galaxy S21 Ultra
  • Samsung Galaxy S22 5G
  • Samsung Galaxy S22 Ultra 5G
  • Samsung Galaxy S22+ 5G
  • Samsung Galaxy S23
  • Samsung Galaxy S23 Ultra
  • Samsung Galaxy S23+
  • Samsung Galaxy S24
  • Samsung Galaxy S24 Ultra
  • Samsung Galaxy S24+
  • Samsung Galaxy S25
  • Samsung Galaxy S25 Ultra
  • Samsung Galaxy S25+
  • Samsung Galaxy S26
  • Samsung Galaxy S26 Ultra
  • Samsung Galaxy S26+
  • Samsung Galaxy Tab S8
  • Snapdragon 8 Elite Gen 5 QRD
  • Snapdragon 8 Elite QRD
  • Xiaomi 12

Supported Mobile Chipsets

  • Snapdragon® 8 Elite Mobile
  • Snapdragon® 8 Elite Gen 5 Mobile
  • Snapdragon® 8 Gen 1 Mobile
  • Snapdragon® 8 Gen 2 Mobile
  • Snapdragon® 8 Gen 3 Mobile
  • Snapdragon® 888 Mobile

Looking for more? See models created by industry leaders.

Discover Model Makers