Real-Time Interactive Video Generation
Overview
The field studies how to generate video that responds as people interact, including controllable worlds, avatars, and live video editing. Common approaches adapt video diffusion or autoregressive models for causal streaming, then use few-step distillation, caching, and bounded memory to reduce latency; 3D geometry and physics can provide more explicit camera and action control. Systems are tested for visual quality, control accuracy, throughput, and latency, with benchmarks increasingly measuring long streams and interactive responsiveness. A central challenge is balancing fast reactions with realistic motion and consistent scenes or identities over long interactions, where drift and limited memory remain concerns.
Latest papers
79 papers19 papers in the last four weeks, up 217% on the four weeks before. 0.1% of all new papers.