Bin-ze

scene rotation

1

When I use Vuer to visualize a 3dgs scene and drag the mouse, the scene will rotate around the specified world axis. before： after： But this will cause the camera...

add new camera to existing sparse scene

1

I used pixsfm to obtain the camera pose of a new image through Ransac+PnP, and the image is exactly the same size and sensor captured as the reconstructed image. How...

I used pixsfm to obtain the camera pose of a new image through Ransac+PnP, and the image is exactly the same size and sensor captured as the reconstructed image. How...

Is additional input required besides the image?

2

I read this paper, it's great work! I have some small questions： 1. When using LoFTR in the coarse reconstruction stage, are the weights of the matcher fixed in this...

I want to integrate this project into a project that depends on mmcv2.x or above, but there is a dependency conflict. I want to know how to expand it. Can...

Great work! I tried to use this algorithm to infer the video. First I detected the people in the video and cropped the people area to 256*256 size. What I...

I tried fine-tuning from a known colmap model: echo "hloc extract_features" echo "+++++++++++++++++++++++++++++++++++++++++" python -m hloc.extract_features --image_dir $image_dir --feature_path $feature_path --export_dir $export_dir # echo "colmap model_converter" # echo "+++++++++++++++++++++++++++++++++++++++++" #...

I want to use dad and dedode for feature extraction, and then use roma for feature point matching to achieve more robust matching and help downstream sfm tasks. Now I...