CJ Ye

Question about Scan2CAD_h5 object

1

Thanks for your great work. I have some questions about the data preparation. I want to use this work for real 3D scan retrival, as the paper shows. I wonder...

A Large-scale Aligned Shape Annotation on ARKitScenes is released!

2

AI can now recreate detailed digital twins of your spaces! 🏠 We built LASA, 10K precise furnishing annotations aligned to most ARKitScenes scans. 🪑 Our DisCo method fuses inputs to...

Expiration of the Download Links

8

Thanks for your nice job! The download links provided for the shared folder on Google Drive (https://drive.google.com/drive/folders/1-DhVDNjPc1l8Vu9Qt_yMbHnpC9OEUa-q?usp=sharing) have expired. If possible, could you please provide me with a valid download...

Thank you for providing the excellent dataset! I downloaded some of the release data and noticed the image IDs differ from the ScanNet IDs. Is there a mapping between the...

Thanks for your great work! I am running your code with pretrained checkpoints. However, after I download the weights from your provide links, it seems the tar file is broken...

Excuse me! It is very lucky for me to read your code about SphereNet. After read your code, I found that there's no block of codes about 'uniform sampling' in...

ValueError: num_samples should be a positive integer value, but got num_samples=0

1

Hello! I am trying to train RP-R-CNN, but I encounter a problem when runing the training command following the Readme.md. When running ``` CUDA_VISIBLE_DEVICES=0 python tools/train_net.py --cfg cfgs/CIHP/e2e_rp_rcnn_R-50-FPN_3x_ms.yaml ``` I...

Adding support to Matterport3D

8

- [x] Add Matterport3D preprocessing - [x] Add MatterPort3D datasets - [x] Add semseg-spunet-v1m1-0-base configs for MatterPort3D - [x] Update Data Preparation Docs - [x] Add preprocessed data and pretrained...