Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization

arXiv:2402.17470v1 Announce Type: cross
Abstract: Currently, there is a high demand for neural network-based image compression codecs. These codecs employ non-linear transforms to create compact bit representations and facilitate faster coding speeds on devices compared to the hand-crafted transforms used in classical frameworks. The scientific and industrial communities are highly interested in these properties, leading to the standardization effort of JPEG-AI. The JPEG-AI verification model has been released and is currently under development for standardization. Utilizing neural networks, it can …

abstract arxiv coding compression cs.cv cs.lg demand devices distribution eess.iv faster frameworks image implementation industrial linear map network neural network non-linear quality spatial standardization study type