AI for Content Creation

Content creation underpins photography, film and video, gaming, virtual and augmented reality, art, design, fashion, and advertising. In just a few years, generative AI has compressed work that once took hours of painstaking manual effort into seconds of automated or interactive creation. Text-to-image models now produce photorealistic and stylized imagery on demand, while video generation and world models synthesize long, temporally consistent—and increasingly interactive and controllable—clips and environments. Rapid progress in 3D and 4D generation, neural rendering, and Gaussian splatting is bringing the same leap to objects, avatars, and dynamic scenes, and unified multi-modal models now tie together text, image, video, and audio for any-to-any creation. Beyond raw synthesis, the community is advancing instruction-based and controllable editing, real-time and on-device generation, identity- and physics-consistent results, and agentic pipelines that plan and compose creative tasks. These capabilities also raise pressing questions of control, attribution, safety, and bias—while offering powerful new sources of synthetic training data for downstream vision tasks in 2D, video, and 3D.

The AI for Content Creation workshop explores this exciting and fast-moving research area. We bring together invited speakers of world-class expertise in content creation, up-and-coming researchers, and authors of submitted workshop papers, to engage in a day filled with learning, discussion, and network building.