# PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond

arXiv: https://arxiv.org/abs/2409.19772 · HTML: https://mlsanity.com/paper/2409.19772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 29 Sep 2024.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera](https://mlsanity.com/paper/1811.10180/) (2018)
- [DDD17: End-To-End DAVIS Driving Dataset](https://mlsanity.com/paper/1711.01458/) (2017)
- [Event Enhanced High-Quality Image Recovery](https://mlsanity.com/paper/2007.08336/) (2020)
- [DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction](https://mlsanity.com/paper/2005.08605/) (2020)
- [E-CIR: Event-Enhanced Continuous Intensity Recovery](https://mlsanity.com/paper/2203.01935/) (2022)
- [Learning specialized activation functions with the Piecewise Linear Unit](https://mlsanity.com/paper/2104.03693/) (2021)
- [DeblurSR: Event-Based Motion Deblurring Under the Spiking Representation](https://mlsanity.com/paper/2303.08977/) (2023)

## Abstract (arXiv)

We present Parametric Piecewise Linear Networks (PPLNs) for temporal vision inference. Motivated by the neuromorphic principles that regulate biological neural behaviors, PPLNs are ideal for processing data captured by event cameras, which are built to simulate neural activities in the human retina. We discuss how to represent the membrane potential of an artificial neuron by a parametric piecewise linear function with learnable coefficients. This design echoes the idea of building deep models from learnable parametric functions recently popularized by Kolmogorov-Arnold Networks (KANs). Experiments demonstrate the state-of-the-art performance of PPLNs in event-based and image-based vision applications, including steering prediction, human pose estimation, and motion deblurring. The source code of our implementation is available at https://github.com/chensong1995/PPLN.