We introduce the new task of 3D object localization in RGB-D scans using natural language descriptions. As input, we assume a point cloud of a scanned 3D scene along with a free-form description of a specified target object. To address this task, we propose ScanRefer, where the core idea is to learn a fused descriptor from 3D object proposals and encoded sentence embeddings. This learned descriptor then correlates the language expressions with the underlying geometric features of the 3D scan and facilitates the regression of the 3D bounding box of the target object. In order to train and benchmark our method, we introduce a new ScanRefer dataset, containing 46,173 descriptions of 9,943 objects from 703 ScanNet scenes. ScanRefer is the first large-scale effort to perform object localization via natural language expression directly in 3D.
Please also check out the project video here.
For additional detail, please see the ScanRefer paper:
"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language"
by Dave Zhenyu Chen, Angel X. Chang and Matthias Nießner
from Technical University of Munich and Simon Fraser University.
If you would like to access to the ScanRefer dataset, please fill out this form. Once your request is accepted, you will receive an email with the download link.
Note: In addition to language annotations in ScanRefer dataset, you also need to access the original ScanNet dataset. Please refer to the ScanNet project page for more details.
Download the dataset by simply executing the wget command:
wget <download_link>
"scene_id": [ScanNet scene id, e.g. "scene0000_00"],
"object_id": [ScanNet object id (corresponds to "objectId" in ScanNet aggregation file), e.g. "34"],
"object_name": [ScanNet object name (corresponds to "label" in ScanNet aggregation file), e.g. "coffee_table"],
"ann_id": [description id, e.g. "1"],
"description": [...],
"token": [a list of tokens from the tokenized description]
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:
cd lib/pointnet2
python setup.py install
Before moving on to the next step, please don't forget to set the project root path to the CONF.PATH.BASE
in lib/config.py
.
- Download the ScanRefer dataset and unzip it under
data/
- Downloadand the preprocessed GLoVE embeddings and put them under
data/
- Download the ScanNetV2 dataset and put (or link)
scans/
under (or to)data/scannet/scans/
After this step, there should be folders containing the ScanNet scene data under the
data/scannet/scans/
with names likescene0000_00
- Pre-process ScanNet data. A folder named
scannet_data/
will be generated underdata/scannet/
after running the following command:
cd data/scannet/
python batch_load_scannet_data.py
- Download the preprocessed multiview features and put it under
data/scannet/scannet_data/
To train the ScanRefer model with multiview features:
python scripts/train.py --use_multiview
For more training options, please run scripts/train.py -h
.
To evaluate the trained ScanRefer models, please find the folder under outputs/
with the current timestamp and run:
python scripts/eval.py --folder <folder_name> --use_multiview
Note that the flags must match the ones set before training. The training information is stored in outputs/<folder_name>/info.json
To predict the localization results predicted by the trained ScanRefer model in a specific scene, please find the corresponding folder under outputs/
with the current timestamp and run:
python scripts/visualize.py --folder <folder_name> --scene_id <scene_id> --use_multiview
Note that the flags must match the ones set before training. The training information is stored in outputs/<folder_name>/info.json
. The output .ply
files will be stored under vis/<scene_id>/
If you use the ScanRefer data or code in your work, please kindly cite our work and the original ScanNet paper:
@misc{chen2019scanrefer,
title={ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language},
author={Dave Zhenyu Chen and Angel X. Chang and Matthias Nießner},
year={2019},
eprint={1912.08830},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@inproceedings{dai2017scannet,
title={Scannet: Richly-annotated 3d reconstructions of indoor scenes},
author={Dai, Angela and Chang, Angel X and Savva, Manolis and Halber, Maciej and Funkhouser, Thomas and Nie{\ss}ner, Matthias},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={5828--5839},
year={2017}
}
We would like to thank facebookresearch/votenet for the 3D object detection codebase and erikwijmans/Pointnet2_PyTorch for the CUDA accelerated PointNet++ implementation.
ScanRefer is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.
Copyright (c) 2020 Dave Zhenyu Chen, Angel X. Chang, Matthias Nießner