# A Differentiable Recurrent Surface for Asynchronous Event-Based Data

arXiv: https://arxiv.org/abs/2001.03455 · HTML: https://mlsanity.com/paper/2001.03455/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jan 2020.

## Built on by (most cited first, 11 of 11)

- [Learning Dense and Continuous Optical Flow from an Event Camera](https://mlsanity.com/paper/2211.09078/) (2022)
- [A Voxel Graph CNN for Object Classification with Event Cameras](https://mlsanity.com/paper/2106.00216/) (2021)
- [Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras](https://mlsanity.com/paper/2211.12324/) (2022)
- [EventDrop: data augmentation for event-based learning](https://mlsanity.com/paper/2106.05836/) (2021)
- [Emergent Visual Sensors for Autonomous Vehicles](https://mlsanity.com/paper/2205.09383/) (2022)
- [Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation](https://mlsanity.com/paper/2303.09919/) (2023)
- [DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation](https://mlsanity.com/paper/2103.12768/) (2021)
- [Event-LSTM: An Unsupervised and Asynchronous Learning-based Representation for Event-based Data](https://mlsanity.com/paper/2105.04216/) (2021)
- [Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification](https://mlsanity.com/paper/2308.11937/) (2023)
- [Neural Implicit Event Generator for Motion Tracking](https://mlsanity.com/paper/2111.03824/) (2021)
- [AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision](https://mlsanity.com/paper/2103.11645/) (2021)

## Abstract (arXiv)

Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes. Differently from classic vision devices, they produce a sparse representation of the scene. Therefore, to apply standard computer vision algorithms, events need to be integrated into a frame or event-surface. This is usually attained through hand-crafted grids that reconstruct the frame using ad-hoc heuristics. In this paper, we propose Matrix-LSTM, a grid of Long Short-Term Memory (LSTM) cells that efficiently process events and learn end-to-end task-dependent event-surfaces. Compared to existing reconstruction approaches, our learned event-surface shows good flexibility and expressiveness on optical flow estimation on the MVSEC benchmark and it improves the state-of-the-art of event-based object classification on the N-Cars dataset.