search

AllenXiangX / SnowflakeNet

(TPAMI 2023) Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer
MIT License
142 stars 16 forks source link

About dataset of Completion3D #8

Closed qinglew closed 2 years ago

qinglew commented 2 years ago

In utils/data_loaders.py, the dataset class always return the partial point cloud and grount truth point cloud. But when I try to inference using pretrained models, an error occurs. This is because for testing split, there is no ground truth data, i.e. /path/to/datasets/Completion3D/test/gt doesn't exist. The dataset is download from the link you provided. So, could you please provide the corresponding ground truth of testing split of completion3d?

AllenXiangX commented 2 years ago

In utils/data_loaders.py, the dataset class always return the partial point cloud and grount truth point cloud. But when I try to inference using pretrained models, an error occurs. This is because for testing split, there is no ground truth data, i.e. /path/to/datasets/Completion3D/test/gt doesn't exist. The dataset is download from the link you provided. So, could you please provide the corresponding ground truth of testing split of completion3d?

I'm sorry there is no ground truth files of testing split on Completion3D, you can change the data_loader to avoid the inference error.