# Neuromorphic Camera Denoising using Graph Neural Network-driven Transformers

arXiv: https://arxiv.org/abs/2112.09685 · HTML: https://mlsanity.com/paper/2112.09685/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras](https://mlsanity.com/paper/1802.06898/) (2018)
- [Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios](https://mlsanity.com/paper/1709.06310/) (2017)
- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [Rethinking Knowledge Graph Propagation for Zero-Shot Learning](https://mlsanity.com/paper/1805.11724/) (2018)
- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras](https://mlsanity.com/paper/1903.07520/) (2019)
- [EVDodgeNet: Deep Dynamic Obstacle Dodging with Event Cameras](https://mlsanity.com/paper/1906.02919/) (2019)
- [Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras](https://mlsanity.com/paper/2003.08282/) (2020)
- [CED: Color Event Camera Dataset](https://mlsanity.com/paper/1904.10772/) (2019)
- [Event-driven Vision and Control for UAVs on a Neuromorphic Chip](https://mlsanity.com/paper/2108.03694/) (2021)
- [End-to-End Multi-Channel Transformer for Speech Recognition](https://mlsanity.com/paper/2102.03951/) (2021)
- [Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks](https://mlsanity.com/paper/2002.11867/) (2020)
- [Neuromorphic Eye-in-Hand Visual Servoing](https://mlsanity.com/paper/2004.07398/) (2020)
- [Real-Time Grasping Strategies Using Event Camera](https://mlsanity.com/paper/2107.07200/) (2021)
- [A Message-Passing Algorithm for Graph Isomorphism](https://mlsanity.com/paper/1704.00395/) (2017)

## Built on by (most cited first, 15 of 15)

- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [Graph Transformers: A Survey](https://mlsanity.com/paper/2407.09777/) (2024)
- [Event-based Monocular Dense Depth Estimation with Recurrent Transformers](https://mlsanity.com/paper/2212.02791/) (2022)
- [Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach](https://mlsanity.com/paper/2506.13083/) (2025)
- [LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising](https://mlsanity.com/paper/2405.19718/) (2024)
- [A Neuromorphic Vision-Based Measurement for Robust Relative Localization in Future Space Exploration Missions](https://mlsanity.com/paper/2206.11541/) (2022)
- [E-Calib: A Fast, Robust and Accurate Calibration Toolbox for Event Cameras](https://mlsanity.com/paper/2306.09078/) (2023)
- [Within-Camera Multilayer Perceptron DVS Denoising](https://mlsanity.com/paper/2304.07543/) (2023)
- [Simultaneous Motion And Noise Estimation with Event Cameras](https://mlsanity.com/paper/2504.04029/) (2025)
- [Neuromorphic Vision-based Motion Segmentation with Graph Transformer Neural Network](https://mlsanity.com/paper/2404.10940/) (2024)
- [Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural Network](https://mlsanity.com/paper/2305.03640/) (2023)
- [Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement](https://mlsanity.com/paper/2402.09270/) (2024)
- [A Bird's-Eye Tutorial of Graph Attention Architectures](https://mlsanity.com/paper/2206.02849/) (2022)
- [An Event-Oriented Diffusion-Refinement Method for Sparse Events Completion](https://mlsanity.com/paper/2401.03153/) (2024)
- [High Throughput Event Filtering: The Interpolation-based DIF Algorithm Hardware Architecture](https://mlsanity.com/paper/2506.05825/) (2025)

## Abstract (arXiv)

Neuromorphic vision is a bio-inspired technology that has triggered a paradigm shift in the computer-vision community and is serving as a key-enabler for a multitude of applications. This technology has offered significant advantages including reduced power consumption, reduced processing needs, and communication speed-ups. However, neuromorphic cameras suffer from significant amounts of measurement noise. This noise deteriorates the performance of neuromorphic event-based perception and navigation algorithms. In this paper, we propose a novel noise filtration algorithm to eliminate events which do not represent real log-intensity variations in the observed scene. We employ a Graph Neural Network (GNN)-driven transformer algorithm, called GNN-Transformer, to classify every active event pixel in the raw stream into real-log intensity variation or noise. Within the GNN, a message-passing framework, called EventConv, is carried out to reflect the spatiotemporal correlation among the events, while preserving their asynchronous nature. We also introduce the Known-object Ground-Truth Labeling (KoGTL) approach for generating approximate ground truth labels of event streams under various illumination conditions. KoGTL is used to generate labeled datasets, from experiments recorded in chalenging lighting conditions. These datasets are used to train and extensively test our proposed algorithm. When tested on unseen datasets, the proposed algorithm outperforms existing methods by 8.8% in terms of filtration accuracy. Additional tests are also conducted on publicly available datasets to demonstrate the generalization capabilities of the proposed algorithm in the presence of illumination variations and different motion dynamics. Compared to existing solutions, qualitative results verified the superior capability of the proposed algorithm to eliminate noise while preserving meaningful scene events.