The sgaligner from whuhxb

SGAligner : 3D Scene Alignment with Scene Graphs

Sayan Deb Sarkar¹, Ondrej Miksik², Marc Pollefeys^1,2, Daniel Barath¹, Iro Armeni¹

¹ETH Zurich ²Microsoft Mixed Reality & AI Labs

SGAligner aligns 3D scene graphs of environments using multi-modal learning and leverage the output for the downstream task of 3D point cloud registration.

[Project Webpage] [Paper]

News 📰

1. May 2023: SGAligner preprint released on arXiv.
10. April 2023: Code released.

Code Structure 🎬

├── sgaligner
│   ├── data-preprocessing            <- subscan generation + preprocessing
│   ├── configs                       <- configuration files
│   ├── src
│   │   │── aligner                   <- SGAligner modules
│   │   │── datasets                  <- dataloader for 3RScan subscans
│   │   │── engine                    <- trainer classes
│   │   │── GeoTransformer            <- geotransformer submodule for registration
│   │   │── inference                 <- inference files for alignment + downstream applications
│   │   │── trainers                  <- train + validation loop (EVA + SGAligner)
│   │── utils                         <- util functions
│   │── README.md                    
│   │── scripts                       <- bash scripts for data generation + preprocesing + training
│   └── output                        <- folder that stores models and logs
│

Dependencies 📝

The main dependencies of the project are the following:

python: 3.8.15
cuda: 11.6

You can set up a conda environment as follows :

git clone --recurse-submodules -j8 [email protected]:sayands/sgaligner.git
cd sgaligner
conda env create -f req.yml

Please follow the submodule for additional installation requirements and setup of GeoTransformer.

Downloads 💧

The pre-trained model and other meta files are available here.

Dataset Generation 🔨

After installing the dependencies, we preprocess the datasets and provide the benchmarks.

Subscan Pair Generation - 3RScan + 3DSSG

Download 3RScan and 3DSSG. Move all files of 3DSSG to a new files/ directory within Scan3R. The structure should be:

├── 3RScan
│   ├── files       <- all 3RScan and 3DSSG meta files (NOT the scan data)  
│   ├── scenes      <- scans
│   └── out         <- Default output directory for generated subscans (created when running pre-processing)

Change the absolute paths in utils/define.py.

First, we create sub-scans from each 3RScan scan using the ground truth scene Graphs from the 3DSSG dataset and then calculate the pairwise overlap ratio for the subscans in a scan. Finally, we preprocess the data for our framework. The relevant code can be found in the data-preprocessing/ directory. You can use the following command to generate the subscans.

bash scripts/generate_data_scan3r_gt.sh

Note To adhere to our evaluation procedure, please do not change the seed value in the files in configs/ directory.

Generating Overlapping and Non-Overlapping Subscan Pairs

To generate overlapping and non-overlapping pairs, use :

python preprocessing/gen_all_pairs_fileset.py

This will create a fileset with the same number of randomly chosen non-overlapping pairs from the generated subscans as overlapping pairs generated before during subscan generation.

Usage on Predicted Scene Graphs : Coming Soon!

Training 🚄

To train SGAligner on 3RScan subscans generated from here, you can use :

cd src
python trainers/trainval_sgaligner.py --config ../configs/scan3r/scan3r_ground_truth.yaml

EVA Training

We also provide training scripts for EVA, used as a baseline after being adapted for scene graph alignment. To train EVA similar to SGAligner on the same data, you can use :

cd src
python trainers/trainval_eva.py --config ../configs/scan3r/scan3r_eva.yaml

We provide config files for the corresponding data in config/ directory. Please change the parameters in the configuration files, if you want to tune the hyper-parameters.

Evaluation 🚦

Graph Alignment + Point Cloud Registration

cd src
python inference/sgaligner/inference_align_reg.py --config ../configs/scan3r/scan3r_ground_truth.yaml --snapshot <path to SGAligner trained model> --reg_snapshot <path to GeoTransformer model trained on 3DMatch>

Finding Overlapping vs Non-Overlapping Pairs

❗ Run Generating Overlapping and Non-Overlapping Subscan Pairs before.

To run the inference, you need to:

cd src
python inference/sgaligner/inference_find_overlapper.py --config ../configs/scan3r/scan3r_gt_w_wo_overlap.yaml --snapshot <path to SGAligner trained model> --reg_snapshot <path to GeoTransformer model trained on 3DMatch>

3D Point Cloud Mosaicking

First, we generate the subscans per 3RScan scan using :

python data-preprocessing/gen_scan_subscan_mapping.py --split <the split you want to generate the mapping for>

And then, to run the inference, you need to:

cd src
python inference/sgaligner/inference_mosaicking.py --config ../configs/scan3r/scan3r_gt_mosaicking.yaml --snapshot <path to SGAligner trained model> --reg_snapshot <path to GeoTransformer model trained on 3DMatch>

Benchmark 📈

We provide detailed results and comparisons here.

3D Scene Graph Alignment (Node Matching)

Method	Mean Reciprocal Rank	Hits@1	Hits@2	Hits@3	Hits@4	Hits@5
EVA	0.867	0.790	0.884	0.938	0.963	0.977
$\mathcal{P}$	0.884	0.835	0.886	0.921	0.938	0.951
$\mathcal{P}$ + $\mathcal{S}$	0.897	0.852	0.899	0.931	0.945	0.955
$\mathcal{P}$ + $\mathcal{S}$ + $\mathcal{R}$	0.911	0.861	0.916	0.947	0.961	0.970
SGAligner	0.950	0.923	0.957	0.974	0.9823	0.987

3D Point Cloud Registration

Method	CD	RRE	RTE	FMR	RR
GeoTr	0.02247	1.813	2.79	98.94	98.49
Ours, K=1	0.01677	1.425	2.88	99.85	98.79
Ours, K=2	0.01111	1.012	1.67	99.85	99.40
Ours, K=3	0.01525	1.736	2.55	99.85	98.81

TODO 🔜

~~Add 3D Point Cloud Mosaicking~~
~~Add Support For EVA~~
Add a demo for real-life point cloud testing
Add usage on Predicted Scene Graphs
Add scene graph alignment of local 3D scenes to prior 3D maps
Add overlapping scene finder with a traditional retrieval method (FPFH + VLAD + KNN)

BibTeX 🙏

@misc{sarkar2023sgaligner,
      title={SGAligner : 3D Scene Alignment with Scene Graphs}, 
      author={Sayan Deb Sarkar and Ondrej Miksik and Marc Pollefeys and Daniel Barath and Iro Armeni},
      year={2023},
      eprint={2304.14880},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgments ♻️

In this project we use (parts of) the official implementations of the following works and thank the respective authors for open sourcing their methods:

SceneGraphFusion (3RScan Dataloader)
GeoTransformer (Registration)
MCLEA (Alignment)

whuhxb / sgaligner Goto Github PK

sgaligner's Introduction