NAFSSR: Stereo Image Super-Resolution Using NAFNet
Paper • 2204.08714 • Published
NAFSSR: Optimized for Qualcomm Devices
NAFNET is designed for lightweight real-time upscaling of images.
This is based on the implementation of NAFSSR found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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 | float | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit NAFSSR on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models 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 NAFSSR on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.super_resolution
Model Stats:
- Model checkpoint: NAFSSR-S_2x
- Input resolution: 128x128
- Number of parameters: 1.54M
- Model size (float): 6.2 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 79.577 ms | 7 - 7 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 199.528 ms | 42 - 42 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 127.996 ms | 6 - 13 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 233.727 ms | 4 - 18 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 188.714 ms | 0 - 41 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 233.727 ms | 4 - 18 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 77.718 ms | 5 - 12 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 194.022 ms | 3 - 6 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 100.087 ms | 4 - 12 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8750 | 100.087 ms | 4 - 12 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS7181 | 199.528 ms | 42 - 42 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 64.536 ms | 3 - 3 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 189.582 ms | 35 - 35 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 118.006 ms | 2 - 9 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 180.586 ms | 0 - 42 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 202.245 ms | 0 - 7 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 61.552 ms | 2 - 9 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 1592.309 ms | 0 - 6 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 183.764 ms | 2 - 4 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 85.542 ms | 2 - 9 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS7790 | 202.245 ms | 0 - 7 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8750 | 85.542 ms | 2 - 9 MB | NPU |
| NAFSSR | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS7181 | 189.582 ms | 35 - 35 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 79.799 ms | 0 - 0 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 199.242 ms | 0 - 0 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 127.792 ms | 1 - 7 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 235.697 ms | 1 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 | 355.445 ms | 1 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 188.009 ms | 1 - 2 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 235.697 ms | 1 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 77.807 ms | 0 - 8 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 355.445 ms | 1 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 193.788 ms | 0 - 4 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 100.571 ms | 1 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 228.173 ms | 1 - 6 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8750 | 100.571 ms | 1 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | float | Qualcomm® QCS7181 | 199.242 ms | 0 - 0 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 64.962 ms | 0 - 0 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 189.815 ms | 0 - 0 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 117.689 ms | 1 - 8 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 | 299.524 ms | 0 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 179.93 ms | 1 - 2 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 202.149 ms | 0 - 6 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 61.603 ms | 0 - 9 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 299.524 ms | 0 - 10 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 1662.723 ms | 0 - 7 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 183.551 ms | 0 - 3 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 85.497 ms | 1 - 9 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS7790 | 202.149 ms | 0 - 6 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8750 | 85.497 ms | 1 - 9 MB | NPU |
| NAFSSR | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS7181 | 189.815 ms | 0 - 0 MB | NPU |
License
- The license for the original implementation of NAFSSR can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.