# EDeNN: Event Decay Neural Networks for low latency vision

arXiv: https://arxiv.org/abs/2209.04362 · HTML: https://mlsanity.com/paper/2209.04362/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 9 Sep 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras](https://mlsanity.com/paper/1802.06898/) (2018)
- [End-to-End Learning of Representations for Asynchronous Event-Based Data](https://mlsanity.com/paper/1904.08245/) (2019)
- [The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM](https://mlsanity.com/paper/1610.08336/) (2016)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [AEGNN: Asynchronous Event-based Graph Neural Networks](https://mlsanity.com/paper/2203.17149/) (2022)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences](https://mlsanity.com/paper/1610.09513/) (2016)
- [Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks](https://mlsanity.com/paper/2106.01862/) (2021)
- [Spiking Deep Networks with LIF Neurons](https://mlsanity.com/paper/1510.08829/) (2015)
- [Event-Based Angular Velocity Regression with Spiking Networks](https://mlsanity.com/paper/2003.02790/) (2020)
- [PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection](https://mlsanity.com/paper/2012.10412/) (2020)
- [Partial Convolution based Padding](https://mlsanity.com/paper/1811.11718/) (2018)
- [Powerline Tracking with Event Cameras](https://mlsanity.com/paper/2108.00515/) (2021)
- [EVReflex: Dense Time-to-Impact Prediction for Event-based Obstacle Avoidance](https://mlsanity.com/paper/2109.00405/) (2021)
- [Noisy Softplus: an activation function that enables SNNs to be trained as ANNs](https://mlsanity.com/paper/1706.03609/) (2017)

## Built on by (most cited first, 1 of 1)

- [CERiL: Continuous Event-based Reinforcement Learning](https://mlsanity.com/paper/2302.07667/) (2023)

## Abstract (arXiv)

Despite the success of neural networks in computer vision tasks, digital 'neurons' are a very loose approximation of biological neurons. Today's learning approaches are designed to function on digital devices with digital data representations such as image frames. In contrast, biological vision systems are generally much more capable and efficient than state-of-the-art digital computer vision algorithms. Event cameras are an emerging sensor technology which imitates biological vision with asynchronously firing pixels, eschewing the concept of the image frame. To leverage modern learning techniques, many event-based algorithms are forced to accumulate events back to image frames, somewhat squandering the advantages of event cameras. We follow the opposite paradigm and develop a new type of neural network which operates closer to the original event data stream. We demonstrate state-of-the-art performance in angular velocity regression and competitive optical flow estimation, while avoiding difficulties related to training SNN. Furthermore, the processing latency of our proposed approach is less than 1/10 any other implementation, while continuous inference increases this improvement by another order of magnitude.