# Superevents: Towards Native Semantic Segmentation for Event-based Cameras

arXiv: https://arxiv.org/abs/2105.06091 · HTML: https://mlsanity.com/paper/2105.06091/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 13 May 2021.

## Builds on (most cited first, 15 of 15)

- [The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM](https://mlsanity.com/paper/1610.08336/) (2016)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [Pyramid Feature Attention Network for Saliency detection](https://mlsanity.com/paper/1903.00179/) (2019)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [EV-SegNet: Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/1811.12039/) (2018)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Superpixels: An Evaluation of the State-of-the-Art](https://mlsanity.com/paper/1612.01601/) (2016)
- [DART: Distribution Aware Retinal Transform for Event-based Cameras](https://mlsanity.com/paper/1710.10800/) (2017)
- [EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning](https://mlsanity.com/paper/2003.07640/) (2020)
- [Star Tracking using an Event Camera](https://mlsanity.com/paper/1812.02895/) (2018)
- [Learning to Super Resolve Intensity Images from Events](https://mlsanity.com/paper/1912.01196/) (2019)
- [Feedforward semantic segmentation with zoom-out features](https://mlsanity.com/paper/1412.0774/) (2014)
- [Event-based Star Tracking via Multiresolution Progressive Hough Transforms](https://mlsanity.com/paper/1906.07866/) (2019)
- [EBBIOT: A Low-complexity Tracking Algorithm for Surveillance in IoVT Using Stationary Neuromorphic Vision Sensors](https://mlsanity.com/paper/1910.01851/) (2019)
- [A low-power end-to-end hybrid neuromorphic framework for surveillance applications](https://mlsanity.com/paper/1910.09806/) (2019)

## Built on by (most cited first, 6 of 6)

- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection](https://mlsanity.com/paper/2304.13455/) (2023)
- [Efficient Human Pose Estimation via 3D Event Point Cloud](https://mlsanity.com/paper/2206.04511/) (2022)
- [Event-aided Semantic Scene Completion](https://mlsanity.com/paper/2502.02334/) (2025)
- [Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder](https://mlsanity.com/paper/2204.07280/) (2022)

## Abstract (arXiv)

Most successful computer vision models transform low-level features, such as Gabor filter responses, into richer representations of intermediate or mid-level complexity for downstream visual tasks. These mid-level representations have not been explored for event cameras, although it is especially relevant to the visually sparse and often disjoint spatial information in the event stream. By making use of locally consistent intermediate representations, termed as superevents, numerous visual tasks ranging from semantic segmentation, visual tracking, depth estimation shall benefit. In essence, superevents are perceptually consistent local units that delineate parts of an object in a scene. Inspired by recent deep learning architectures, we present a novel method that employs lifetime augmentation for obtaining an event stream representation that is fed to a fully convolutional network to extract superevents. Our qualitative and quantitative experimental results on several sequences of a benchmark dataset highlights the significant potential for event-based downstream applications.