AI RESEARCH
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
arXiv CS.CV
•
ArXi:2605.06051v1 Announce Type: new Camera-controlled video-to-video (V2V) generation enables dynamic viewpoint synthesis from monocular footage, holding immense potential for interactive filmmaking and live broadcasting. However, existing implicit synthesis methods fundamentally rely on non-causal, full-sequence processing and rigid prefix-style temporal concatenation. This architectural paradigm mandates bidirectional attention, resulting in prohibitive computational latency, quadratic complexity scaling, and inherent incompatibility with real-time streaming or variable-length inputs.