Perturbed State Space Feature Encoders for Optical Flow with Event Cameras

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Raju, Gokul Raju Govinda, Zubić, Nikola, Cannici, Marco, Scaramuzza, Davide
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916690937249792
author Raju, Gokul Raju Govinda
Zubić, Nikola
Cannici, Marco
Scaramuzza, Davide
author_facet Raju, Gokul Raju Govinda
Zubić, Nikola
Cannici, Marco
Scaramuzza, Davide
contents With their motion-responsive nature, event-based cameras offer significant advantages over traditional cameras for optical flow estimation. While deep learning has improved upon traditional methods, current neural networks adopted for event-based optical flow still face temporal and spatial reasoning limitations. We propose Perturbed State Space Feature Encoders (P-SSE) for multi-frame optical flow with event cameras to address these challenges. P-SSE adaptively processes spatiotemporal features with a large receptive field akin to Transformer-based methods, while maintaining the linear computational complexity characteristic of SSMs. However, the key innovation that enables the state-of-the-art performance of our model lies in our perturbation technique applied to the state dynamics matrix governing the SSM system. This approach significantly improves the stability and performance of our model. We integrate P-SSE into a framework that leverages bi-directional flows and recurrent connections, expanding the temporal context of flow prediction. Evaluations on DSEC-Flow and MVSEC datasets showcase P-SSE's superiority, with 8.48% and 11.86% improvements in EPE performance, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Perturbed State Space Feature Encoders for Optical Flow with Event Cameras
Raju, Gokul Raju Govinda
Zubić, Nikola
Cannici, Marco
Scaramuzza, Davide
Computer Vision and Pattern Recognition
Machine Learning
With their motion-responsive nature, event-based cameras offer significant advantages over traditional cameras for optical flow estimation. While deep learning has improved upon traditional methods, current neural networks adopted for event-based optical flow still face temporal and spatial reasoning limitations. We propose Perturbed State Space Feature Encoders (P-SSE) for multi-frame optical flow with event cameras to address these challenges. P-SSE adaptively processes spatiotemporal features with a large receptive field akin to Transformer-based methods, while maintaining the linear computational complexity characteristic of SSMs. However, the key innovation that enables the state-of-the-art performance of our model lies in our perturbation technique applied to the state dynamics matrix governing the SSM system. This approach significantly improves the stability and performance of our model. We integrate P-SSE into a framework that leverages bi-directional flows and recurrent connections, expanding the temporal context of flow prediction. Evaluations on DSEC-Flow and MVSEC datasets showcase P-SSE's superiority, with 8.48% and 11.86% improvements in EPE performance, respectively.
title Perturbed State Space Feature Encoders for Optical Flow with Event Cameras
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2504.10669