--- title: CenterNet-3D canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-3D" md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-3D.md" repository: Qualcomm-AI-Hub/CenterNet-3D last_updated: 2026-10-16 license: mit downloads: 0 stars: 0 tags: - android --- # CenterNet-3D > CenterNet-3D - Qualcomm-AI-Hub 在 ModelScope 开源的模型。CenterNet-3D: Optimized for Qualcomm Devices Qualcomm-AI-Hub/CenterNet-3D 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。 - **Repository**: Qualcomm-AI-Hub/CenterNet-3D - **License**: mit - **Tags**: android - **Downloads**: 0 - **Stars**: 0 - **Last updated**: 2026-10-16 Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-3D --- ![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/web-assets/model_demo.png) # CenterNet-3D: Optimized for Qualcomm Devices CenterNet is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle. This is based on the implementation of CenterNet-3D found [here](https://github.com/xingyizhou/CenterNet). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_3d) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.cn) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device. ## Getting Started There are two ways to deploy this model on your device: ### Option 1: Download Pre-Exported Models Below are pre-exported model assets ready for deployment. | Runtime | Precision | Chipset | SDK Versions | Download | |---|---|---|---|---| | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen1.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_qcs8275.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip) | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip) | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip) | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip) | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen1.zip) | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_qcs8275.zip) | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip) | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_sa8775p.zip) | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_qcs9075.zip) | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_sa7255p.zip) | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_sa8295p.zip) | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip) | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_3d/releases/v0.62.1/centernet_3d-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) For more device-specific assets and performance metrics, visit **[CenterNet-3D on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/centernet_3d)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_3d) Python library to compile and export the model with your own: - Custom weights (e.g., fine-tuned checkpoints) - Custom input shapes - Target device and runtime configurations This option is ideal if you need to customize the model beyond the default configuration provided here. See our repository for [CenterNet-3D on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_3d) for usage instructions. ## Model Details **Model Type:** Model_use_case.driver_assistance **Model Stats:** - Input resolution: 1 x 3 x 384 x 1280 - Model checkpoint: ddd_3dop.pth - Model size: 79 MB - Number of parameters: 20.6M ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 840.663 ms | 5 - 5 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 1498.139 ms | 54 - 54 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1129.663 ms | 4 - 12 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1778.245 ms | 3 - 18 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1413.596 ms | 2 - 8 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1531.273 ms | 0 - 55 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 1778.245 ms | 3 - 18 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1480.045 ms | 0 - 6 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1498.139 ms | 54 - 54 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1024.66 ms | 1 - 13 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 1024.66 ms | 1 - 13 MB | NPU | CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 908.746 ms | 2 - 13 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 839.477 ms | 3 - 3 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 1500.565 ms | 3 - 3 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1132.361 ms | 3 - 12 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1811.482 ms | 3 - 12 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1414.005 ms | 3 - 9 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1534.179 ms | 4 - 5 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 1502.523 ms | 2 - 10 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 1502.523 ms | 2 - 10 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 1502.523 ms | 2 - 10 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 1811.482 ms | 3 - 12 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1480.173 ms | 3 - 8 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1500.565 ms | 3 - 3 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1016.755 ms | 3 - 12 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 2417.946 ms | 1 - 10 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 1425.882 ms | 1 - 6 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 1016.755 ms | 3 - 12 MB | NPU | CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 908.708 ms | 0 - 10 MB | NPU ## License * The license for the original implementation of CenterNet-3D can be found [here](https://github.com/xingyizhou/CenterNet/blob/master/LICENSE). ## References * [Objects as Points](https://arxiv.org/abs/1904.07850) * [Source Model Implementation](https://github.com/xingyizhou/CenterNet) ## Community * For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).