This repository contains code that implements video to events conversion as described in Gehrig et al. CVPR'20 and the used dataset. The paper can be found here
If you use this code in an academic context, please cite the following work:
Daniel Gehrig, Mathias Gehrig, Javier Hidalgo-Carrió, Davide Scaramuzza, "Video to Events: Recycling Video Datasets for Event Cameras", The Conference on Computer Vision and Pattern Recognition (CVPR), 2020
@InProceedings{Gehrig_2020_CVPR,
author = {Daniel Gehrig and Mathias Gehrig and Javier Hidalgo-Carri\'o and Davide Scaramuzza},
title = {Video to Events: Recycling Video Datasets for Event Cameras},
booktitle = {{IEEE} Conf. Comput. Vis. Pattern Recog. (CVPR)},
month = {June},
year = {2020}
}
- We release a web app and interactive demo which generates events and converts your webcam to events. Try it out here.
- We now also release new python bindings for esim with GPU support. Details are here
Try out our the interactive demo and webcam support here.
The synthetic N-Caltech101 dataset, as well as video sequences used for event conversion can be found here. For each sample of each class it contains events in the form class/image_%04d.npz
and images in the form class/image_%05d/images/image_%05d.png
, as well as the corresponding timestamps of the images in class/image_%04d/timestamps.txt
.
Clone the repo recursively with submodules
git clone [email protected]:uzh-rpg/rpg_vid2e.git --recursive
Installation with Anaconda
conda config --add channels pytorch
conda config --append channels conda-forge
conda create --name vid2e --file requirements.txt
conda install -y -c conda-forge pybind11 matplotlib
Build the python bindings for ESIM
pip install esim_py/
Build the python bindings with GPU support with
pip install esim_torch/
This package provides code for adaptive upsampling with frame interpolation based on Super-SloMo
Consult the README for detailed instructions and examples.
This package exposes python bindings for ESIM which can be used within a training loop.
For detailed instructions and example consult the README
This package exposes python bindings for ESIM with GPU support.
For detailed instructions and example consult the README
To run an example, first upsample the example videos
device=cpu
# device=cuda:0
python upsampling/upsample.py --input_dir=example/original --output_dir=example/upsampled --device=$device
This will generate upsampling/upsampled with in the example/upsampled
folder. To generate events, use
python esim_torch/generate_events.py --input_dir=example/upsampled \
--output_dir=example/events \
--contrast_threshold_neg=0.2 \
--contrast_threshold_pos=0.2 \
--refractory_period_ns=0