# Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolution

arXiv: https://arxiv.org/abs/2508.03244 · HTML: https://mlsanity.com/paper/2508.03244/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (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)
- [Feedback Network for Image Super-Resolution](https://mlsanity.com/paper/1903.09814/) (2019)
- [Graph-Based Object Classification for Neuromorphic Vision Sensing](https://mlsanity.com/paper/1908.06648/) (2019)
- [Efficient Video Super-Resolution through Recurrent Latent Space Propagation](https://mlsanity.com/paper/1909.08080/) (2019)
- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2203.14186/) (2022)
- [Are High-Resolution Event Cameras Really Needed?](https://mlsanity.com/paper/2203.14672/) (2022)
- [Event Camera Based Real-Time Detection and Tracking of Indoor Ground Robots](https://mlsanity.com/paper/2102.11916/) (2021)
- [Towards End-to-End Neuromorphic Event-based 3D Object Reconstruction Without Physical Priors](https://mlsanity.com/paper/2501.00741/) (2025)
- [A Survey of 3D Reconstruction with Event Cameras](https://mlsanity.com/paper/2505.08438/) (2025)
- [Bilateral Event Mining and Complementary for Event Stream Super-Resolution](https://mlsanity.com/paper/2405.10037/) (2024)
- [Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion](https://mlsanity.com/paper/2406.19640/) (2024)
- [Event-Stream Super Resolution using Sigma-Delta Neural Network](https://mlsanity.com/paper/2408.06968/) (2024)

## Built on by (most cited first, 3 of 3)

- [Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation](https://mlsanity.com/paper/2512.06306/) (2025)
- [FracEvent: Event-Camera Simulation via Fractional-Relaxation Pixel Dynamics](https://mlsanity.com/paper/2606.26636/) (2026)
- [EvLIR: Learning Illumination Residuals from Ordered Events for Low-Light Image Enhancement](https://mlsanity.com/paper/2606.29430/) (2026)

## Abstract (arXiv)

Event cameras offer unparalleled advantages such as high temporal resolution, low latency, and high dynamic range. However, their limited spatial resolution poses challenges for fine-grained perception tasks. In this work, we propose an ultra-lightweight, stream-based event-to-event super-resolution method based on Spiking Neural Networks (SNNs), designed for real-time deployment on resource-constrained devices. To further reduce model size, we introduce a novel Dual-Forward Polarity-Split Event Encoding strategy that decouples positive and negative events into separate forward paths through a shared SNN. Furthermore, we propose a Learnable Spatio-temporal Polarity-aware Loss (LearnSTPLoss) that adaptively balances temporal, spatial, and polarity consistency using learnable uncertainty-based weights. Experimental results demonstrate that our method achieves competitive super-resolution performance on multiple datasets while significantly reducing model size and inference time. The lightweight design enables embedding the module into event cameras or using it as an efficient front-end preprocessing for downstream vision tasks.