TMA: Temporal Motion Aggregation for Event-based Optical Flow

by   Haotian Liu, et al.

Event cameras have the ability to record continuous and detailed trajectories of objects with high temporal resolution, thereby providing intuitive motion cues for optical flow estimation. Nevertheless, most existing learning-based approaches for event optical flow estimation directly remould the paradigm of conventional images by representing the consecutive event stream as static frames, ignoring the inherent temporal continuity of event data. In this paper, we argue that temporal continuity is a vital element of event-based optical flow and propose a novel Temporal Motion Aggregation (TMA) approach to unlock its potential. Technically, TMA comprises three components: an event splitting strategy to incorporate intermediate motion information underlying the temporal context, a linear lookup strategy to align temporally continuous motion features and a novel motion pattern aggregation module to emphasize consistent patterns for motion feature enhancement. By incorporating temporally continuous motion information, TMA can derive better flow estimates than existing methods at early stages, which not only enables TMA to obtain more accurate final predictions, but also greatly reduces the demand for a number of refinements. Extensive experiments on DESC-Flow and MVSEC datasets verify the effectiveness and superiority of our TMA. Remarkably, compared to E-RAFT, TMA achieves a 6 improvement in accuracy and a 40


page 1

page 5

page 9


Learning Dense and Continuous Optical Flow from an Event Camera

Event cameras such as DAVIS can simultaneously output high temporal reso...

Event-based Temporally Dense Optical Flow Estimation with Sequential Neural Networks

Prior works on event-based optical flow estimation have investigated sev...

Towards Anytime Optical Flow Estimation with Event Cameras

Event cameras are capable of responding to log-brightness changes in mic...

EV-MGRFlowNet: Motion-Guided Recurrent Network for Unsupervised Event-based Optical Flow with Hybrid Motion-Compensation Loss

Event cameras offer promising properties, such as high temporal resoluti...

Optical Flow Estimation via Motion Feature Recovery

Optical flow estimation with occlusion or large displacement is a proble...

Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform

In this work, we propose a novel transformation for events from an event...

Estimating motion with principal component regression strategies

In this paper, two simple principal component regression methods for est...

Please sign up or login with your details

Forgot password? Click here to reset