Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion

TL;DR

This paper introduces RMFNet, a novel recursive multi-branch fusion network for event stream super-resolution that separates and fuses positive and negative events, significantly improving accuracy and efficiency.

Contribution

The paper proposes a new recursive multi-branch fusion approach with feature fusion and exchange modules to better utilize positive and negative event information for super-resolution.

Findings

Achieves over 17% and 31% improvements on synthetic and real datasets.

Provides a 2.3X acceleration in processing speed.

Outperforms existing methods in object recognition and video reconstruction.

Abstract

Current Event Stream Super-Resolution (ESR) methods overlook the redundant and complementary information present in positive and negative events within the event stream, employing a direct mixing approach for super-resolution, which may lead to detail loss and inefficiency. To address these issues, we propose an efficient Recursive Multi-Branch Information Fusion Network (RMFNet) that separates positive and negative events for complementary information extraction, followed by mutual supplementation and refinement. Particularly, we introduce Feature Fusion Modules (FFM) and Feature Exchange Modules (FEM). FFM is designed for the fusion of contextual information within neighboring event streams, leveraging the coupling relationship between positive and negative events to alleviate the misleading of noises in the respective branches. FEM efficiently promotes the fusion and exchange of information between positive and negative branches, enabling superior local information enhancement and global information complementation. Experimental results demonstrate that our approach achieves over 17% and 31% improvement on synthetic and real datasets, accompanied by a 2.3X acceleration. Furthermore, we evaluate our method on two downstream event-driven applications, \emph{i.e.}, object recognition and video reconstruction, achieving remarkable results that outperform existing methods. Our code and Supplementary Material are available at https://github.com/Lqm26/RMFNet.