RayDer enables static-scene NVS from dynamic internet video, scaling like an LLM

CSProfKGD · x · 2026-08-27

RayDer introduces a new method to learn static-scene novel view synthesis (NVS) directly from unposed, messy, and dynamic real-world internet videos. Traditional self-supervised NVS breaks on such dynamic content, but RayDer overcomes these limitations. This allows scaling NVS training on massive web video data, similar to how LLMs scale on text.

Original post →

More from Research

Research channel →