Summary - F.748.73 (06/2026) - Framework, requirements and evaluation of a media content enhancement and media editing system based on multimodal foundation models

Media content enhancement and media editing with the support of multimodal foundation models can meet new media service requirements such as fine-grained real scene matting and solve issues such as efficiency and quality.
Recommendation ITU-T F.748.73 specifies the framework, requirements and evaluation of a media content enhancement and media editing system based on multimodal foundation models. The system consists of a media capability support component and a media capability component. The media capability support component includes multimodal foundation models, specialized models and text, and audio, video and image processing. The media capability component includes media collection and gathering, media editing, media content enhancement, media production, media utilization and media resource management. It can guide industry implementation and interoperability by different stakeholders.