Jun-xiong Cai

What's the difference between raw label and label-filt for 2D semantic benchmark?

2

Whether should I choose the 'label' or 'label-filt' for 2D semantic lable benchmark

color mode in face parsing module

1

I notice that the normailize parameters "mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225]" should be apply on PIL color mode (RGB). While in 'dataset', i found that images are loaded with Opencv...

The predicted semantic mask has a slight offset.

2

When I test the new published pretrained model, I found that semantic segmentation results and input images do not match perfectly. I looked through the'tanh_warp'-related processing and found that the...

render_laplacian has modify the gaussian scale from 'pc.get_scaling' to 'pc.get_scaling * pc.get_shape'. https://github.com/ajhamdi/ges-splatting/blob/c05fc7dbb22e270a5a6f490e7040adac4af02c96/gaussian_renderer/__init__.py#L150C9-L150C47 so when store laplacian module to gaussian ply the raw scale should be "scale = self.scaling_inverse_activation(self.get_scaling *...