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 2.51, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.51 Download
TFLITE float Universal QAIRT 2.51 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Depth-Anything-V3 ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 27.378 ms 2 - 446 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 31.079 ms 2 - 439 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® X2 Elite 24.479 ms 5 - 5 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® X Elite 60.112 ms 70 - 70 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Gen 3 Mobile 43.884 ms 0 - 563 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Gen 1 Mobile 87.714 ms 1 - 582 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ IQ-8275 65.583 ms 3 - 10 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 59.311 ms 3 - 82 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® QCS8450 87.714 ms 1 - 582 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ IQ-9075 65.172 ms 3 - 10 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ IQ-X7181 60.112 ms 70 - 70 MB NPU
Depth-Anything-V3 ONNX float Qualcomm® Dragonwing™ Q-8750 31.079 ms 2 - 439 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Elite Extreme Gen 6 Mobile 18.018 ms 5 - 444 MB NPU
Depth-Anything-V3 ONNX float Snapdragon® 8 Elite Gen 6 Mobile 32.833 ms 5 - 440 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 27.631 ms 3 - 452 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 36.703 ms 0 - 437 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® X2 Elite 27.944 ms 3 - 3 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® X Elite 66.881 ms 3 - 3 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 48.897 ms 2 - 575 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 95.189 ms 3 - 568 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 71.462 ms 3 - 10 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 65.478 ms 3 - 570 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8775P 72.275 ms 1 - 429 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8650P 72.275 ms 1 - 429 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8255P 72.275 ms 1 - 429 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® QCS8450 95.189 ms 3 - 568 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 72.859 ms 3 - 10 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 66.881 ms 3 - 3 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 36.703 ms 0 - 437 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA7255P 160.468 ms 1 - 430 MB NPU
Depth-Anything-V3 QNN_DLC float Qualcomm® SA8295P 104.628 ms 0 - 411 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Elite Extreme Gen 6 Mobile 20.533 ms 3 - 442 MB NPU
Depth-Anything-V3 QNN_DLC float Snapdragon® 8 Elite Gen 6 Mobile 36.207 ms 3 - 436 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 29.337 ms 1 - 458 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 36.318 ms 1 - 453 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Gen 3 Mobile 44.498 ms 1 - 553 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Gen 1 Mobile 100.643 ms 0 - 547 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ IQ-8275 65.896 ms 1 - 82 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 61.029 ms 1 - 7 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8775P 954.78 ms 24 - 40 MB CPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8650P 954.78 ms 24 - 40 MB CPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8255P 954.78 ms 24 - 40 MB CPU
Depth-Anything-V3 TFLITE float Qualcomm® QCS8450 100.643 ms 0 - 547 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ IQ-9075 67.672 ms 1 - 81 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® Dragonwing™ Q-8750 36.318 ms 1 - 453 MB NPU
Depth-Anything-V3 TFLITE float Qualcomm® SA8295P 100.472 ms 1 - 409 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Elite Extreme Gen 6 Mobile 21.685 ms 1 - 440 MB NPU
Depth-Anything-V3 TFLITE float Snapdragon® 8 Elite Gen 6 Mobile 33.007 ms 1 - 426 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. 🙋 1 Ask for provider support

Paper for qualcomm/Depth-Anything-V3