metadata
license: mit
language:
- en
base_model:
- magicleap/superpoint
pipeline_tag: image-feature-extraction
tags:
- Axera
- NPU
- Pulsar2
- SuperPoint
- Computer-Vision
SuperPoint on Axera NPU
This repository contains the SuperPoint model converted to run on the Axera NPU. SuperPoint is a self-supervised framework for training interest point detectors and descriptors, suitable for a large number of multiple-view geometry problems in computer vision.
This version has been quantized using w8a16 and is optimized for use with Pulsar2 (version 4.2).
Convert Tools Links
For developers interested in custom model conversion or optimization:
- AXera Platform GitHub Repo: Comprehensive guides and sample code for AXera chips.
- Pulsar2 Documentation: Official guide on converting ONNX models to
.axmodel.
Supported Platforms
- AX650
- AX637
| Chips | SuperPoint (640x480) |
|---|---|
| AX650 | xxx ms |
| AX637 | 96.118 ms |
How to Use
Download the model files and the inference binary to your Axera-powered device:
root@ax650:~/SuperPoint-Demo# tree
.
|-- ax650
| `-- superpoint.axmodel
|-- ax_superpoint
|-- input1.jpg
|-- input2.jpg
`-- output.jpg
Inference
Inference with AX650 Host
Output image
Inference with AX637 Host