# Removing the Compute Bottleneck for Event-based Visual Place Recognition with Spiking Neural Networks

arXiv: https://arxiv.org/abs/2610.16022 · HTML: https://mlsanity.com/paper/2610.16022/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [A Survey of Neuromorphic Computing and Neural Networks in Hardware](https://mlsanity.com/paper/1705.06963/) (2017)
- [Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline](https://mlsanity.com/paper/2304.06793/) (2023)
- [A Survey on Efficient Training of Transformers](https://mlsanity.com/paper/2302.01107/) (2023)
- [Event-based visual place recognition with ensembles of temporal windows](https://mlsanity.com/paper/2006.02826/) (2020)
- [How Many Events do You Need? Event-based Visual Place Recognition Using Sparse But Varying Pixels](https://mlsanity.com/paper/2206.13673/) (2022)
- [Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments](https://mlsanity.com/paper/2010.00716/) (2020)
- [Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments](https://mlsanity.com/paper/2109.06452/) (2021)
- [Dataset and Benchmark: Novel Sensors for Autonomous Vehicle Perception](https://mlsanity.com/paper/2401.13853/) (2024)
- [Anatomy Of High-Performance Deep Learning Convolutions On SIMD Architectures](https://mlsanity.com/paper/1808.05567/) (2018)
- [Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2312.09028/) (2023)
- [A Systematic Survey of General Sparse Matrix-Matrix Multiplication](https://mlsanity.com/paper/2002.11273/) (2020)
- [A compact neuromorphic system for ultra-energy-efficient, on-device robot localization](https://mlsanity.com/paper/2408.16754/) (2024)
- [Highly-Efficient Binary Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2202.12375/) (2022)
- [VPRTempo: A Fast Temporally Encoded Spiking Neural Network for Visual Place Recognition](https://mlsanity.com/paper/2309.10225/) (2023)
- [Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognition](https://mlsanity.com/paper/2604.03277/) (2026)
- [Prepare for Warp Speed: Sub-millisecond Visual Place Recognition Using Event Cameras](https://mlsanity.com/paper/2509.24094/) (2025)

## Abstract (arXiv)

Neuromorphic sensing and computing promise low latency and high energy efficiency for robotics, yet most event-based visual place recognition (VPR) pipelines reintroduce dense, frame-like computation downstream of an inherently sparse sensor, forfeiting the sensor's latency advantage. In this paper, we address the problem of resolving an event-based VPR query in tens of microseconds on a commodity CPU. We train a two-layer spiking neural network (SNN) with additive spike-timing-dependent plasticity (STDP), which drives the learned weight matrix towards a strongly bimodal distribution, amenable to aggressive magnitude pruning. At inference, our pipeline exploits this sparsity by reading only the pruned weights corresponding to the query's active pixels. As surviving weights share a near-uniform magnitude, each neuron's score reduces to an integer count of matching synapses instead of a weighted sum, lowering per-query latency. This computation is small enough to remain resident in a CPU's fast on-chip cache. On three event-based VPR benchmarks, our sparse SNN exceeds the recall of LENS, an existing event-based SNN, while reducing per-query latency by 5.5-6.2x to tens of microseconds. It matches the recall of a dense variant of our network and of the sum-of-absolute-differences (SAD) baseline, while reading 10x fewer weights than the dense variant. We further characterise how recall and latency scale with the number of active pixels and reference places. These results suggest that the sparsity of both event-based input and learned weights can already be exploited for low-latency inference on conventional processors.