A Perspective on Deep Vision Performance with Standard Image and Video Codecs

arXiv:2404.12330v1 Announce Type: new
Abstract: Resource-constrained hardware, such as edge devices or cell phones, often rely on cloud servers to provide the required computational resources for inference in deep vision models. However, transferring image and video data from an edge or mobile device to a cloud server requires coding to deal with network constraints. The use of standardized codecs, such as JPEG or H.264, is prevalent and required to ensure interoperability. This paper aims to examine the implications of employing …

abstract arxiv cloud computational cs.cv cs.mm data devices edge edge devices hardware however image inference mobile mobile device performance perspective phones resources server servers standard type video video data vision vision models