387-u-red-unsupervised-3d-shape-retrieval-and-deformation-for-partial-point-clouds
Science Score: 31.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.4%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
·
Repository
Basic Info
- Host: GitHub
- Owner: SZU-AdvTech-2024
- Default Branch: main
- Size: 0 Bytes
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Created over 1 year ago
· Last pushed over 1 year ago
Metadata Files
Citation
https://github.com/SZU-AdvTech-2024/387-U-RED-Unsupervised-3D-Shape-Retrieval-and-Deformation-for-Partial-Point-Clouds/blob/main/
## Data download and preprocessing details
Please follow [joint_learning_retrieval_deformation](https://github.com/mikacuy/joint_learning_retrieval_deformation) to prepare the dataset and reorder the directory like:
```
your_base_dir/
data_aabb_all_models/
data_aabb_constraints_keypoint/
dis_mat/
generated_datasplits/
partnet_rgb_masks_chair/
partnet_rgb_masks_storagefurniture/
partnet_rgb_masks_table/
```
## Setup
```
pip install -r requirements.txt
```
## Configs
Modify the config files in folder 'config'. Complete the value occupied by 'xxx' including "base_dir" and "log_path" in training config and "dm_model_path", "re_model_path", "base_dir" and "log_path" in testing config. During testing phase, keep "dm_model_path" and "re_model_path" exactly the same as the trained model. If you want to change the category, just fix "category" into "storagefurniture" or "table".
## Train
```
CUDA_VISIBLE_DEVICES=0 python engine/train.py config/config_train_chair.json
```
## Test
```
CUDA_VISIBLE_DEVICES=0 python engine/test.py config/config_test_chair.json
```
## Visualization
```
CUDA_VISIBLE_DEVICES=0 python engine/vis.py config/config_vis_chair.json
```
Owner
- Name: SZU-AdvTech-2024
- Login: SZU-AdvTech-2024
- Kind: organization
- Repositories: 1
- Profile: https://github.com/SZU-AdvTech-2024
Citation (citation.txt)
@inproceedings{REPO387,
author = "Di, Yan and Zhang, Chenyangguang and Zhang, Ruida and Manhardt, Fabian and Su, Yongzhi and Rambach, Jason and Stricker, Didier and Ji, Xiangyang and Tombari, Federico",
booktitle = "Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)",
month = "October",
pages = "8884-8895",
title = "{U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds}",
year = "2023"
}
GitHub Events
Total
- Push event: 2
- Create event: 3
Last Year
- Push event: 2
- Create event: 3