English | 简体中文
Lingdong Kong1,2 Youquan Liu3 Lai Xing Ng4 Benoit R. Cottereau5,6 Wei Tsang Ooi1 1National University of Singapore 2CNRS@CREATE 3Hochschule Bremerhaven 4Institute for Infocomm Research, A*STAR 5IPAL, CNRS IRL 2955, Singapore 6CerCo, CNRS UMR 5549, Universite Toulouse III
OpenESS
is an open-vocabulary event-based semantic segmentation (ESS) framework that synergizes information from image, text, and event-data domains to enable scalable ESS in an open-world, annotation-efficient manner.
Input Event Stream | “Driveable” | “Car” | “Manmade” |
Zero-Shot ESS | “Walkable” | “Barrier” | “Flat” |
Demo #1 | Demo #2 | Demo #3 |
---|---|---|
[YouTube]() :arrow_heading_up: | [YouTube]() :arrow_heading_up: | [YouTube]() :arrow_heading_up: |
Kindly refer to INSTALL.md for the installation details.
Kindly refer to DATA_PREPARE.md for the details to prepare the [DDD17-Seg]() and [DSEC-Semantic]() datasets.
Please refer to GET_STARTED.md to learn more about how to use this codebase.
To be updated.
To be updated.
To be updated.
To be updated.
If you find this work helpful, please kindly consider citing our paper:
@inproceedings{kong2024openess,
title = {OpenESS: Event-Based Semantic Scene Understanding with Open Vocabularies},
author = {Kong, Lingdong and Liu, Youquan and Ng, Lai Xing and Cottereau, Benoit R. and Ooi, Wei Tsang},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2024},
}
This work is under the Apache License Version 2.0, while some specific implementations in this codebase might be with other licenses. Kindly refer to LICENSE.md for a more careful check, if you are using our code for commercial matters.
To be updated.