Skip to content

wffancy/3dssg

Repository files navigation

3dssg

3D scene graph generation using GCN

reproduction of CVPR2020 "Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions"

Setup

The code works under pytorch 1.6.0 with only one card supported. Execute the following command to install PyTorch:

conda install pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=10.2 -c pytorch

Install the necessary packages listed out in requirements.txt:

pip install -r requirements.txt

After all packages are properly installed, please run the following commands to compile the CUDA modules for the PointNet++ backbone (optional, the default code doesn't use this):

cd lib/pointnet2
python setup.py install

Usage

Train the default GCN model with the following command:

python scripts/train.py

It also makes sense to change the hyperparameters using command line arguments like --batch_size, --epoch etc.
Use argument --use_pretrained to load pretrained model. Use argument --vis for visualization and the results will be saved under vis folder.

Visualization

Scene-id: 7747a50c-9431-24e8-877d-e60c3a341cc2

7747a50c-9431-24e8-877d-e60c3a341cc2

Scene-id: 43b8cadf-6678-2e38-9920-064144c99406

43b8cadf-6678-2e38-9920-064144c99406

Scene-id: ba6fdaaa-a4c1-2dca-8163-a52b18bf6b64

ba6fdaaa-a4c1-2dca-8163-a52b18bf6b64

About

3D scene graph generation using GCN

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published