JingruiYu

Problem with generating dictionary on own features

1

Hello, I use my own CNN generated 512 dimension uchar descriptors of 7000 images and use DBoW3::Vocabulary vocab; vocab.create( descriptors ); vocab.save( "vocabulary.gz" ); to generate dictionary. Then I use...

Is this net a NeRF model for this line of code in the pose_estimation.ipynb file? `# Encode. net.encode( input_image.unsqueeze(0), input_pose.unsqueeze(0).to(device=device), focal, )` Are the parameters of this NeRF model modified...

NetEase Musicer interface is not available

1

Great job, but the NetEase Musicer interface is not available. How to solve this problem? `musicer) ➜ Musicer git:(main) ✗ python main.py ### ### ### ### ###### ###### ###### ########...

Precision degradation issues

9

**Configuration** model: [v0.1.3_end2end](https://github.com/fabio-sim/LightGlue-ONNX/releases/download/v0.1.3/superpoint_2048_lightglue_end2end.onnx) **python** code: v0.1.3, command is `python infer.py --img_paths assets/DSC_0410.JPG assets/DSC_0411.JPG --img_size 1024 --lightglue_path weights_test/superpoint_2048_lightglue_end2end.onnx --extractor_type superpoint --viz` result image is  **c++** code: using master branch, onnxruntime...

Very good work! However, it is hard to know how use your tool. It would be helpful if you could add some example. Thanks!

How to fine-tune DPVO on your own dataset and achieve better results？

14

Hello, Great work! so I tried it on my own dataset, but the results are quite strange. I prepared the data in the format of TartanAir. Under each scene folder,...

**Dear Maintainers,** First, I would like to express my appreciation for this well-designed project. The code structure and implementation details are truly impressive! --- ### **Question Regarding Gij Definition** In...