Zexin He

Results 23 comments of Zexin He

Hi, Thanks for your interest! The data preparation and processing for MVImgNet are rather complicated and involve logics that are not mentioned in the original LRM paper. Therefore, we do...

Hi, Plz refer to this issue https://github.com/3DTopia/OpenLRM/issues/2#issuecomment-1882590904. There isn't much differences for V1.1 models. Plz also note that you can also use less resources, e.g. 8 A100 GPUs, by configuring...

Hi, Thanks for your interest! We're using a fixed focal length so that training and inference would share this same fov setting and impose no extra need for GT camera...