search

astra-vision / MonoScene

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image
https://astra-vision.github.io/MonoScene/
Apache License 2.0
708 stars 69 forks source link

custom dataset #90

Closed lucianzhong closed 10 months ago

lucianzhong commented 10 months ago

Hi, thanks for this great work.

By given custom dataset's camera intrinsic and extrinsic, is it possible to inference directly without training the model?

Best regards

anhquancao commented 10 months ago

Yes, that's what I did to get Fig. 9 in the paper.

lucianzhong commented 10 months ago

Thanks for replay. I will check Fig. 9 in the paper.