SOTAVerified

Event-based vision

An event camera, also known as a neuromorphic camera, silicon retina or dynamic vision sensor, is an imaging sensor that responds to local changes in brightness. Event cameras do not capture images using a shutter as conventional cameras do. Instead, each pixel inside an event camera operates independently and asynchronously, reporting changes in brightness as they occur and staying silent otherwise. Modern event cameras have microsecond temporal resolution, 120 dB dynamic range, and less under/overexposure and motion blur than frame cameras.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 131–140 of 145 papers

TitleStatusHype
Density Invariant Contrast Maximization for Neuromorphic Earth ObservationsCode0
GERD: Geometric event response data generationCode0
Focus Is All You Need: Loss Functions For Event-based VisionCode0
Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based VisionCode0
Event TransformerCode0
Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion PerceptionCode0
Event Cameras, Contrast Maximization and Reward Functions: An AnalysisCode0
Event-based Vision for Early Prediction of Manipulation ActionsCode0
CrossZoom: Simultaneously Motion Deblurring and Event Super-ResolvingCode0
TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based VisionCode0
Show:102550
← PrevPage 14 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1REDmAP43—Unverified