Camera-Controlled Video Generation

Camera-controlled video generation studies how to make a generated or re-shot video follow a desired camera path, from simple pans and orbits to long-horizon navigation. Approaches condition diffusion or autoregressive models on camera poses, geometric cues such as depth and point tracks, or persistent 3D and visual memories; language-based planners can also turn cinematic intent into trajectories. Evaluation increasingly tests camera adherence alongside visual quality, cross-view consistency, and whether scenes remain stable on revisits, using benchmarks with real and synthetic videos. The main tension is that stronger geometric control and long-term consistency can conflict with photorealism, dynamic scene changes, and fast interactive generation.