https://github.com/tub-rip/e2fai
Project page of the paper: "Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras"
https://github.com/tub-rip/e2fai
Last synced: 8 months ago
JSON representation
Project page of the paper: "Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras"
- Host: GitHub
- URL: https://github.com/tub-rip/e2fai
- Owner: tub-rip
- Created: 2025-03-21T10:48:44.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2025-03-25T09:01:14.000Z (11 months ago)
- Last Synced: 2025-03-25T10:21:49.485Z (11 months ago)
- Size: 2.11 MB
- Stars: 6
- Watchers: 2
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- event-vision-index - E2FAI: **E**vents to **F**low **A**nd **I**ntensity (ICCV 2025) - rip/e2fai?style=social"/> (Optical Flow Estimation)
README
# Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras
Official repository for [**Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras**](https://arxiv.org/abs/2503.17262), by [Shuang Guo](https://shuang1997.github.io), [Friedhelm Hamann](https://friedhelmhamann.github.io/) and [Guillermo Gallego](http://www.guillermogallego.es).
## Method.
**E2FAI**: **E**vents to **F**low **A**nd **I**ntensity
## Results
### DSEC dataset (640 × 480 px)
### BS-ERGB dataset (970 × 625 px)
## Citation
If you use this work in your research, please cite it as follows:
```bibtex
@Article{Guo25e2fai,
author = {Shuang Guo and Friedhelm Hamann and Guillermo Gallego},
title = {Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras},
journal = {(under review)},
year = 2025
}
```
# Code coming soon...
(under review)
## Setup
### High-level Input-Output
**Input**:
- Events.
**Output**:
- Optical flow.
- Intensity image.
## Related Works
* [Motion-prior Contrast Maximization (ECCV 2024)](https://github.com/tub-rip/MotionPriorCMax)
* [Secrets of Event-Based Optical Flow (TPAMI 2024)](https://github.com/tub-rip/event_based_optical_flow)
* [EVILIP: Event-based Image Reconstruction as a Linear Inverse Problem (TPAMI 2022)](https://github.com/tub-rip/event_based_image_rec_inverse_problem)
* [Event Collapse in Contrast Maximization Frameworks](https://github.com/tub-rip/event_collapse)
## Additional Resources
* [Research page (TU Berlin RIP lab)](https://sites.google.com/view/guillermogallego/research/event-based-vision)
* [EPBA: Event-based Photometric Bundle Adjustment](https://github.com/tub-rip/epba)
* [EMBA: Event-based Mosaicing Bundle Adjustment (ECCV 2024)](https://github.com/tub-rip/emba)
* [CMax-SLAM (TRO 2024)](https://github.com/tub-rip/cmax_slam)
* [ES-PTAM: Event-based Stereo Parallel Tracking and Mapping](https://github.com/tub-rip/ES-PTAM)
* [Course at TU Berlin](https://sites.google.com/view/guillermogallego/teaching/event-based-robot-vision)
* [Survey paper](http://rpg.ifi.uzh.ch/docs/EventVisionSurvey.pdf)
* [List of Resources](https://github.com/uzh-rpg/event-based_vision_resources)