WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

ArXi:2603.29089v1 Announce Type: cross Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a foundational property of flow matching - namely, defining a path of transport between two data distributions - we model 3D generation generally as a problem of flowing through 3D data distributions, not limited to conditional denoising.