Rafael Toledo

Hi, first I'd like to thank you for sharing this work, such amazing research! I was wondering if Is it possible to make the pre-trained model of the multi-illuminant dataset...

Doubt about the XYZ road coordinates and projecting BEV's image.

2

First off, thank you for this incredible work! It's been very insightful for my studies! But, I'm facing a problem when I try to extract the XYZ road coordinates from...

Bad predictions from HuggingFace pretrained models

4

Hi, thanks for sharing this great work. I was trying to use your model based on the HF example [here](https://huggingface.co/docs/transformers/main/en/model_doc/oneformer#transformers.OneFormerForUniversalSegmentation.forward.example). But It turned out that it predicts badly, even trying...

Results on ADE20k

3

Hey, thanks for sharing this work. I wonder if you had a glance of this model results on the ade20k dataset.

Hey, first off, thanks for sharing this work! I noticed that you're actively using Relative Positional Embeddings (RPE) for all attention operations [here](https://github.com/hustvl/ViTMatte/blob/main/configs/common/model.py#L34) and [here](https://github.com/hustvl/ViTMatte/blob/main/modeling/backbone/vit.py#L75). As the RPE are intended...

Question about the matting labeling

1

First off, thanks for sharing your great work. I have a question about how did you get the FG alpha masks, especially for the transparent ones. On the article, you...