WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification

Video world models aim to generate temporally coherent visual observations conditioned on actions, but often suffer from 3D geometric inconsistencies such as spatial drift, object deformation, and perspective violations, which limit their reliability in downstream tasks. We propose WorldPrism, a post-training framework that improves 3D consistency via reinforcement learning without modifying the base model architecture. The central challenge lies in designing a reliable reward signal. To address this, we introduce Bidirectional Geometry-Flow Verification, a bidirectional cross-space mechanism that evaluates consistency through two complementary paths: (i) lifting 2D optical flow into 3D to measure position-space agreement, and (ii) projecting reconstructed 3D geometry to match the point correspondence. By leveraging these two independent and complementary signals, this design mitigates the blind spots of unilateral 2D evaluation. We further incorporate hierarchical temporal evaluation to capture both local and long-range geometric consistency. Experiments on diverse datasets demonstrate that WorldPrism achieves state-of-the-art 3D consistency while preserving visual quality and generative diversity.