GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

3 Vector Institute Original Lane change (4m) Original Editing Input Dolly zoom Driving simulation Single view Inputs Dynamic video Generated video 0 Cameras 4 8 26 39 106 118 Sparse views 12 Cinematic effect 12 22 42 0 4 8 12 69 69 N Frame number Figure 1. GEN3C can generate long and temporally consistent videos with precise camera control. We apply it to various applications, including single-view and sparse-views novel view synthesis, monocular dynamic video novel view synthesis, and driving simulation. With an explicit 3D cache, GEN3C further supports generating videos with cinematic effects, such as Dolly Zoom which simultaneously changes poses and intrinsics, and 3D editing.