Depth Estimation
PyTorch
android

Depth-Anything-V3: Optimized for Qualcomm Devices

Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from arbitrary visual inputs, with or without known camera poses.

This is based on the implementation of Depth-Anything-V3 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
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Depth-Anything-V3 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 Depth-Anything-V3 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

  • Model checkpoint: da3-small
  • Input resolution: 518x518
  • Number of parameters: 24.7M
  • Model size (float): 94.3 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Depth-Anything-V3 ONNX float Snapdragon® X2 Elite 28.173 ms 5 - 5 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® X Elite 70.35 ms 70 - 70 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Gen 3 Mobile 55.259 ms 0 - 651 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Gen 1 Mobile 129.086 ms 6 - 665 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 68.897 ms 0 - 79 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® QCS8450 129.086 ms 6 - 665 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ IQ-9075 76.979 ms 3 - 9 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ IQ-X7181 70.35 ms 70 - 70 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ Q-8750 36.794 ms 2 - 500 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Elite Mobile 36.794 ms 2 - 500 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 28.349 ms 2 - 522 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® X2 Elite 35.227 ms 3 - 3 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® X Elite 78.994 ms 3 - 3 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 60.959 ms 1 - 646 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 150.255 ms 3 - 678 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ QCS8275 186.755 ms 1 - 492 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 78.674 ms 3 - 636 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8775P 85.403 ms 1 - 491 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8650P 85.403 ms 1 - 491 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8255P 85.403 ms 1 - 491 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® QCS8450 150.255 ms 3 - 678 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 86.001 ms 3 - 9 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 78.994 ms 3 - 3 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 43.287 ms 2 - 502 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA7255P 186.755 ms 1 - 492 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8295P 118.827 ms 0 - 505 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Elite Mobile 43.287 ms 2 - 502 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 33.326 ms 3 - 521 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Gen 3 Mobile 54.196 ms 1 - 596 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Gen 1 Mobile 119.041 ms 2 - 612 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ QCS8275 180.621 ms 1 - 467 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 74.406 ms 0 - 613 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8775P 81.119 ms 1 - 467 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8650P 81.119 ms 1 - 467 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8255P 81.119 ms 1 - 467 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® QCS8450 119.041 ms 2 - 612 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ IQ-9075 81.12 ms 1 - 80 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ Q-8750 39.193 ms 1 - 475 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA7255P 180.621 ms 1 - 467 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8295P 103.405 ms 1 - 466 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Elite Mobile 39.193 ms 1 - 475 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 30.804 ms 1 - 488 MB NPU

License

  • The license for the original implementation of Depth-Anything-V3 can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Depth-Anything-V3