Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians

ArXi:2601.00678v2 Announce Type: replace Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications.