A problem about cutting the Stanford automobile data set

ken2576 / vision-nerf

Official PyTorch Implementation of paper "Vision Transformer for NeRF-Based View Synthesis from a Single Input Image", WACV 2023.

MIT License

107 stars 12 forks source link

A problem about cutting the Stanford automobile data set #15

Closed ZhiJieChen02 closed 4 months ago

ZhiJieChen02 commented 9 months ago

Thank your great work！ When I was trying to use the Stanford Automobile Dataset to conduct experiments in real scenarios, I encountered the problem that the data set could not be cut correctly. Could you please help? I need a cut data set.

ken2576 commented 4 months ago

I'm not sure what you mean exactly. But to get better matting, you might need to try out other object segmentation network. Detectron2 is a good repo to start https://github.com/facebookresearch/detectron2