This repository contains a set of tools for working with the Common Objects in 3D (CO3D) dataset. The dataset has been introduced in our ICCV'21 paper: Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction.
The links to all dataset files are present in this repository in co3d_links.txt
.
We also provide a python script that allows downloading all dataset files at once.
In order to do so, execute the download script:
python ./download_dataset.py --download_folder DOWNLOAD_FOLDER
where DOWNLOAD_FOLDER
is a local target folder for downloading the dataset files.
Make sure to create this folder before commencing the download.
This is a Python 3
/ PyTorch
codebase.
- Install
PyTorch
. - Install
PyTorch3D
. - Install the remaining dependencies in
requirements.txt
:
pip install lpips visdom tqdm requests
Note that the core data model in dataset/types.py
is independent of PyTorch
and can be imported and used with other machine-learning frameworks.
- Install dependencies - See Installation above.
- Download the dataset here to a given root folder
DATASET_ROOT_FOLDER
. - In
dataset/dataset_zoo.py
set theDATASET_ROOT
variable to your DATASET_ROOT_FOLDER`:dataset_zoo.py:25: DATASET_ROOT = DATASET_ROOT_FOLDER
- Run
eval_demo.py
:Note thatpython eval_demo.py
eval_demo.py
runs an evaluation of a simple depth-based image rendering (DBIR) model on the same data as in the paper. Hence, the results are directly comparable to the numbers reported in the paper.
Unit tests can be executed with:
python -m unittest
If you use our dataset, please use the following citation:
@inproceedings{reizenstein21co3d,
Author = {Reizenstein, Jeremy and Shapovalov, Roman and Henzler, Philipp and Sbordone, Luca and Labatut, Patrick and Novotny, David},
Booktitle = {International Conference on Computer Vision},
Title = {Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction},
Year = {2021},
}
The CO3D codebase is released under the BSD License.
The following presentation of the dataset was delivered at the Extreme Vision Workshop at CVPR 2021: