A spatiotemporal style transfer algorithm for dynamic visual stimulus generation

arXiv:2403.04940v1 Announce Type: cross
Abstract: Understanding how visual information is encoded in biological and artificial systems often requires vision scientists to generate appropriate stimuli to test specific hypotheses. Although deep neural network models have revolutionized the field of image generation with methods such as image style transfer, available methods for video generation are scarce. Here, we introduce the Spatiotemporal Style Transfer (STST) algorithm, a dynamic visual stimulus generation framework that allows powerful manipulation and synthesis of video stimuli for vision …

abstract algorithm artificial arxiv cs.ai cs.cv cs.lg deep neural network dynamic generate image image generation information network neural network q-bio.nc scientists stimulus style style transfer systems test transfer type understanding vision visual