Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras

TL;DR

This paper introduces a zero-shot event matching model for event cameras that achieves wide-baseline correspondence without target-domain fine-tuning, using a novel attention backbone and synthetic data generation.

Contribution

The authors propose the first zero-shot event matching model capable of cross-dataset wide-baseline correspondence, with a new attention backbone and synthetic data framework.

Findings

Achieves 37.7% improvement over previous methods.

Enables cross-dataset wide-baseline matching without fine-tuning.

Uses a novel motion-robust attention backbone with multi-timescale features.

Abstract

Event cameras have recently shown promising capabilities in instantaneous motion estimation due to their robustness to low light and fast motions. However, computing wide-baseline correspondence between two arbitrary views remains a significant challenge, since event appearance changes substantially with motion, and learning-based approaches are constrained by both scalability and limited wide-baseline supervision. We therefore introduce the first event matching model that achieves cross-dataset wide-baseline correspondence in a zero-shot manner: a single model trained once is deployed on unseen datasets without any target-domain fine-tuning or adaptation. To enable this capability, we introduce a motion-robust and computationally efficient attention backbone that learns multi-timescale features from event streams, augmented with sparsity-aware event token selection, making large-scale training on diverse wide-baseline supervision computationally feasible. To provide the supervision needed for wide-baseline generalization, we develop a robust event motion synthesis framework to generate large-scale event-matching datasets with augmented viewpoints, modalities, and motions. Extensive experiments across multiple benchmarks show that our framework achieves a 37.7% improvement over the previous best event feature matching methods. Code and data are available at: https://github.com/spikelab-jhu/Match-Any-Events.