search

autonomousvision / convolutional_occupancy_networks

[ECCV'20] Convolutional Occupancy Networks
https://pengsongyou.github.io/conv_onet
MIT License
830 stars 113 forks source link

Ground Truth Mesh of the Synthetic Indoor Scene #48

Closed samcao416 closed 2 years ago

samcao416 commented 2 years ago

Hi, I just tried training the synthetic indoor scene with datasets downloaded from the link. It worked well. I want to compare the generated mesh with the ground-truth mesh, however, what I can find is some point clouds that seem to be the ground truth. Therefore, could you please help me with the ground-truth mesh of the synthetic indoor scene? Thanks a lot.

samcao416 commented 2 years ago

Besides, could you please release an example config file of the scan-net dataset? I would like to try training on the more realistic scenes.

pengsongyou commented 2 years ago

Hi @samcao416, you can download the GT synthetic room mesh from the link below. 

wget https://s3.eu-central-1.amazonaws.com/avg-projects/convolutional_occupancy_networks/data/room_watertight_mesh.zip

As for the ScanNet, we did not train on it at all but directly applied the model trained on synthetic rooms to it. You can simply process the data as we mentioned here. Then you can use a pretrained model to directly infer ScanNet.

Best Songyou

samcao416 commented 2 years ago

Got it. Thanks a lot!

Hi @samcao416, you can download the GT synthetic room mesh from the link below.

wget https://s3.eu-central-1.amazonaws.com/avg-projects/convolutional_occupancy_networks/data/room_watertight_mesh.zip

As for the ScanNet, we did not train on it at all but directly applied the model trained on synthetic rooms to it. You can simply process the data as we mentioned here. Then you can use a pretrained model to directly infer ScanNet.

Best Songyou

Got it. Thanks a lot!