WZY99

Question Regarding Image Downscaling Method

3

https://github.com/nerfstudio-project/nerfstudio/blob/9b3cbc79bf239eb3c69e7c288632aab02c4f0bb1/nerfstudio/models/splatfacto.py#L83 Why was the following method chosen for downscaling images instead of directly using [F.resize](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.resize.html)? ```python def resize_image(image: torch.Tensor, d: int): """ Downscale images using the same 'area' method in...

- Automatic downscale_factor calculation. - Implementation of downsampling for RGB, depth, and normal images

Potential Precision Loss When Using Normal Data in PNG Format

1

I would like to bring attention to a potential issue regarding the precision of normal data in the get_normal_filepaths method. https://github.com/maturk/dn-splatter/blob/aa754d80b72a484f69e769113c065a6e78deb24b/dn_splatter/data/coolermap_dataparser.py#L99 Currently, normal data is being stored in .png and...

Hello, @liuff19, Thanks for your great work! I have a question about why ReconX chooses DynamiCrafter as the video diffusion backbone. In fact, there are many alternative video diffusion backbone,...