# Enhancing Visual Place Recognition via Fast and Slow Adaptive Biasing in Event Cameras

arXiv: https://arxiv.org/abs/2403.16425 · HTML: https://mlsanity.com/paper/2403.16425/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [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)
- [Event-based visual place recognition with ensembles of temporal windows](https://mlsanity.com/paper/2006.02826/) (2020)
- [Shining light on the DVS pixel: A tutorial and discussion about biasing and optimization](https://mlsanity.com/paper/2304.04706/) (2023)
- [Feedback control of event cameras](https://mlsanity.com/paper/2105.00409/) (2021)
- [How Many Events do You Need? Event-based Visual Place Recognition Using Sparse But Varying Pixels](https://mlsanity.com/paper/2206.13673/) (2022)
- [Unraveling the paradox of intensity-dependent DVS pixel noise](https://mlsanity.com/paper/2109.08640/) (2021)
- [Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments](https://mlsanity.com/paper/2109.06452/) (2021)
- [Optimal biasing and physical limits of DVS event noise](https://mlsanity.com/paper/2304.04019/) (2023)
- [FE-Fusion-VPR: Attention-based Multi-Scale Network Architecture for Visual Place Recognition by Fusing Frames and Events](https://mlsanity.com/paper/2211.12244/) (2022)
- [Control and Evaluation of Event Cameras Output Sharpness via Bias](https://mlsanity.com/paper/2210.13929/) (2022)
- [Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition](https://mlsanity.com/paper/2209.08723/) (2022)
- [VPRTempo: A Fast Temporally Encoded Spiking Neural Network for Visual Place Recognition](https://mlsanity.com/paper/2309.10225/) (2023)
- [Exploiting Alternating DVS Shot Noise Event Pair Statistics to Reduce Background Activity](https://mlsanity.com/paper/2304.03494/) (2023)
- [ASAP: Adaptive Scheme for Asynchronous Processing of Event-based Vision Algorithms](https://mlsanity.com/paper/2209.08597/) (2022)
- [ASAP: Adaptive Transmission Scheme for Online Processing of Event-based Algorithms](https://mlsanity.com/paper/2209.08602/) (2022)

## Built on by (most cited first, 10 of 10)

- [Ensemble-Based Event Camera Place Recognition Under Varying Illumination](https://mlsanity.com/paper/2509.01968/) (2025)
- [Autobiasing Event Cameras](https://mlsanity.com/paper/2411.00729/) (2024)
- [Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognition](https://mlsanity.com/paper/2604.03277/) (2026)
- [Low-Latency Scalable Streaming for Event-Based Vision](https://mlsanity.com/paper/2412.07889/) (2024)
- [On the Theory of Bias Tuning in Event Cameras](https://mlsanity.com/paper/2501.18788/) (2025)
- [BiasBench: A reproducible benchmark for tuning the biases of event cameras](https://mlsanity.com/paper/2504.18235/) (2025)
- [EventGeM: Global-to-Local Feature Matching for Event-Based Visual Place Recognition](https://mlsanity.com/paper/2603.05807/) (2026)
- [Event-Based Visual Teach-and-Repeat via Fast Fourier-Domain Cross-Correlation](https://mlsanity.com/paper/2509.17287/) (2025)
- [Event Driven Clustering Algorithm](https://mlsanity.com/paper/2602.00115/) (2026)
- [LEAR: Learning Edge-Aware Representations for Event-to-LiDAR Localization](https://mlsanity.com/paper/2603.01839/) (2026)

## Abstract (arXiv)

Event cameras are increasingly popular in robotics due to beneficial features such as low latency, energy efficiency, and high dynamic range. Nevertheless, their downstream task performance is greatly influenced by the optimization of bias parameters. These parameters, for instance, regulate the necessary change in light intensity to trigger an event, which in turn depends on factors such as the environment lighting and camera motion. This paper introduces feedback control algorithms that automatically tune the bias parameters through two interacting methods: 1) An immediate, on-the-fly textitfast adaptation of the refractory period, which sets the minimum interval between consecutive events, and 2) if the event rate exceeds the specified bounds even after changing the refractory period repeatedly, the controller adapts the pixel bandwidth and event thresholds, which stabilizes after a short period of noise events across all pixels (textitslow adaptation). Our evaluation focuses on the visual place recognition task, where incoming query images are compared to a given reference database. We conducted comprehensive evaluations of our algorithms' adaptive feedback control in real-time. To do so, we collected the QCR-Fast-and-Slow dataset that contains DAVIS346 event camera streams from 366 repeated traversals of a Scout Mini robot navigating through a 100 meter long indoor lab setting (totaling over 35km distance traveled) in varying brightness conditions with ground truth location information. Our proposed feedback controllers result in superior performance when compared to the standard bias settings and prior feedback control methods. Our findings also detail the impact of bias adjustments on task performance and feature ablation studies on the fast and slow adaptation mechanisms.