--- library_name: pytorch license: other tags: - android pipeline_tag: depth-estimation --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/web-assets/model_demo.png) # StereoNet: Optimized for Qualcomm Devices StereoNet is an end-to-end deep architecture for real-time stereo matching that produces high-quality, edge-preserved disparity maps from a rectified stereo image pair. This is based on the implementation of StereoNet found [here](https://github.com/andrewlstewart/StereoNet_PyTorch). 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/blob/main/src/qai_hub_models/models/stereonet) 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.com) 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 | |---|---|---|---|---| | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.54.0/stereonet-onnx-float.zip) | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.54.0/stereonet-qnn_dlc-float.zip) | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/stereonet/releases/v0.54.0/stereonet-tflite-float.zip) For more device-specific assets and performance metrics, visit **[StereoNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/stereonet)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/stereonet) 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 [StereoNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/stereonet) for usage instructions. ## Model Details **Model Type:** Model_use_case.depth_estimation **Model Stats:** - Model checkpoint: KeystoneDepth (epoch=21-step=696366.ckpt) - Input resolution: 786x490 - Number of parameters: 1.94M - Model size (float): 7.41 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | StereoNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 184.074 ms | 6 - 1350 MB | NPU | StereoNet | ONNX | float | Snapdragon® 8 Elite Mobile | 218.855 ms | 3 - 1320 MB | NPU | StereoNet | ONNX | float | Snapdragon® X2 Elite | 181.239 ms | 20 - 20 MB | NPU | StereoNet | ONNX | float | Snapdragon® X Elite | 331.458 ms | 20 - 20 MB | NPU | StereoNet | ONNX | float | Snapdragon® X Elite | 331.458 ms | 20 - 20 MB | NPU | StereoNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 260.792 ms | 6 - 1985 MB | NPU | StereoNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 354.11 ms | 0 - 25 MB | NPU | StereoNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 218.855 ms | 3 - 1320 MB | NPU | StereoNet | ONNX | float | Qualcomm® QCS9075 | 513.647 ms | 3 - 6 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 189.713 ms | 3 - 3264 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 237.39 ms | 0 - 3242 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® X2 Elite | 194.502 ms | 3 - 3 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® X Elite | 361.154 ms | 3 - 3 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® X Elite | 361.154 ms | 3 - 3 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 284.403 ms | 3 - 4456 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 447.352 ms | 3 - 6 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® SA8775P | 461.882 ms | 0 - 3260 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® SA8775P | 461.882 ms | 0 - 3260 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® SA8775P | 461.882 ms | 0 - 3260 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® SA7255P | 1293.498 ms | 0 - 3259 MB | NPU | StereoNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 237.39 ms | 0 - 3242 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® SA8295P | 515.621 ms | 0 - 3366 MB | NPU | StereoNet | QNN_DLC | float | Qualcomm® QCS9075 | 511.715 ms | 3 - 9 MB | NPU | StereoNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 297.417 ms | 73 - 3824 MB | NPU | StereoNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 270.062 ms | 73 - 3773 MB | NPU | StereoNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 336.95 ms | 73 - 5322 MB | NPU | StereoNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 534.839 ms | 74 - 77 MB | NPU | StereoNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 270.062 ms | 73 - 3773 MB | NPU | StereoNet | TFLITE | float | Qualcomm® QCS9075 | 663.537 ms | 72 - 202 MB | NPU ## License * The license for the original implementation of StereoNet can be found [here](https://github.com/andrewlstewart/StereoNet_PyTorch/blob/main/LICENSE). ## References * [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://arxiv.org/abs/1807.08865) * [Source Model Implementation](https://github.com/andrewlstewart/StereoNet_PyTorch) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).