accelerated_features icon indicating copy to clipboard operation
accelerated_features copied to clipboard

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

Results 49 accelerated_features issues
Sort by recently updated
recently updated
newest added

1. Support for exporting xfeat, xfeat+matching models. 2. Support for exporting dynamic shapes. 3. Support for exporting a specified version of opset. 4. Add onnxruntime inference demo. | Model |...

Hello @guipotje and team, In this PR, I am adding support for exporting ONNX and TensorRT models. On running the TensorRT engine, we can observe improvement in FPS. Since the...

Hello ! Thank you for your amazing work. I just tried out the code on my system and noticed the following bug: ``` root@ubuntu:/home/xavier01/Documents/workspace/embedded-vpr/accelerated_features# python3 realtime_demo.py --method XFeat [ WARN:0]...

Great work on this project, it looks very promising! What are your thought on using this architecture to find keypoints and descriptors across modalities? [This](https://arxiv.org/pdf/2404.09692) paper attempts to match features...

How do I get two Image matching similarity through these keypoints?

Hello. Thank you for your nice work and contribution of field. I have some questions. 1. How does this method perform if training without Reliability Map? 2. Since the method...

I just found OpenVINO does not support InstanceNorm https://docs.openvino.ai/2023.3/openvino_docs_ops_opset13.html