DeepVID v2: self-supervised denoising with decoupled spatiotemporal enhancement for low-photon voltage imaging
Liu C, Lu J, Wu Y, Ye X, Ahrens A, Platisa J, Pieribone V, Chen J, Tian L. DeepVID v2: self-supervised denoising with decoupled spatiotemporal enhancement for low-photon voltage imaging. Neurophotonics 2024, 11: 045007. PMID: 39474199, PMCID: PMC11519979, DOI: 10.1117/1.nph.11.4.045007.Peer-Reviewed Original ResearchDeep learning denoising methodsLeverage temporal informationSelf-supervised denoisingSuperior denoising capabilitiesReal-time inferenceLocal spatial informationSequence of framesVoltage imaging dataDenoising frameworkDenoising methodSignal-to-noise ratioDenoising capabilityExtraction branchDenoising needsBlind pixelsTemporal informationDenoisingGround truthPoisson noiseTemporal performanceCentral frameOffline versionSpatial informationDynamics of neuronal activitySignal-to-noise