AruniRC
AruniRC
As per the **Training Usage** section, running `./train/fetch_caffe.sh` creates a `./caffe_private_pascal` folder, not a `./caffe-colorization` folder, for caffe installation. So the paths in your training scripts in `./train` should also...
Could you please provide the numbers for PointNet++ part segmentation *without* using normals, i.e. just with *XYZ* points as inputs? I saw all papers report numbers using these normal information,...
Hi, is there any plans for releasing a Tensorflow or Pytorch based version of this codebase? thanks, Aruni
Creating sortable columns with sticky header, and specfiying a path using the href field in Col (different from the image path) does not work. Clicking on the image directs to...
Hi, is there any plans to release a Kubric-pretrained DCV Net, similar to RAFT? thanks.
Great work making this available open source as well as in both TF and PyTorch, @rpautrat ! I noticed that your demo script (superpoint/match_features_demo.py) is for the TF version. It...
**Describe the bug** Using the results from ORB-SLAM2 instead of COLMAP for a sequence from the TUM dataset (freiburg3_long_office_household) is resulting in incorrect camera poses when loaded into Nerfstudio: the...
Hi, It is a great help that you have shared a SPADE model trained on CORD dataset - makes setting up and sanity-checks with this codebase much easier. Any chance...
**Is your feature request related to a problem? Please describe.** I am unable to turn off Viser during training a nerf using Nerfstudio. **Describe the solution you'd like** In some...
Firstly, thank you for your work, @guipotje et al. There are issues like https://github.com/verlab/accelerated_features/issues/59 that show SIFT performing better than vanilla XFeat for large geometric transformations, or when there is...