ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
BEVFusion for 3D Object Detection
Model
NVIDIA
NVIDIA
BEVFusion for 3D Object Detection

BEVFusion model to detect 3D objects from point cloud and RGB data.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application(s) & Domain(s):Object Detection (People).
Model Type:3D Object Detection.
Intended Users:This model is intended for developers working in industrial, robotics, and smart space applications.
Output:3-D Bounding Box(es), Category Label(s), Confidence Score(s)
Describe how the model works:Detects one or more objects from fused LIDAR point cloud features and camera RGB features.
Technical Limitations:This model may not work well for detecting partially or fully occluded persons.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Mean Average Precision (mAP)
Licensing:NVIDIA Open Model License