EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras

TL;DR

EV-FlowNet introduces a self-supervised deep learning approach that estimates optical flow from event-based camera data using an image-based representation and grayscale images as supervisory signals, achieving competitive performance.

Contribution

It presents the first self-supervised neural network for optical flow estimation from event-based cameras, leveraging grayscale images for training without labeled data.

Findings

Accurately predicts optical flow from event data in various scenes.

Performance is competitive with traditional image-based networks.

Provides a framework for applying self-supervised methods to event-based vision.

Abstract

Event-based cameras have shown great promise in a variety of situations where frame based cameras suffer, such as high speed motions and high dynamic range scenes. However, developing algorithms for event measurements requires a new class of hand crafted algorithms. Deep learning has shown great success in providing model free solutions to many problems in the vision community, but existing networks have been developed with frame based images in mind, and there does not exist the wealth of labeled data for events as there does for images for supervised training. To these points, we present EV-FlowNet, a novel self-supervised deep learning pipeline for optical flow estimation for event based cameras. In particular, we introduce an image based representation of a given event stream, which is fed into a self-supervised neural network as the sole input. The corresponding grayscale images captured from the same camera at the same time as the events are then used as a supervisory signal to provide a loss function at training time, given the estimated flow from the network. We show that the resulting network is able to accurately predict optical flow from events only in a variety of different scenes, with performance competitive to image based networks. This method not only allows for accurate estimation of dense optical flow, but also provides a framework for the transfer of other self-supervised methods to the event-based domain.