GeoFix: Geometry Fixing for 4D Consistent Generation

arXiv:2610.14293v1 Announce Type: new Abstract: Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-training by designing geometric rewards, yet this can degrade texture and fine detail, requiring auxiliary appearance rewards and careful reward balancing. To address this challenge, we propose GeoFix, a unified framework that improves geometric consistency and visual quality with a single geometric reward, applicable to both training and inference-time reward alignment. Our reward measures cross-view depth consistency in static scene regions, targeting structural inconsistencies without directly constraining appearance or penalizing valid object motion. Crucially, depth agreement increases with camera field-of-view overlap even in real videos and 4D datasets, allowing a smaller camera movement to be mistaken for better geometry. We account for this effect by calibrating the reward against the overlap-dependent trend. GeoFix achieves a 39% improvement in WorldScore 3D consistency and a 4% increase in VBench Quality Score.

Related

• VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
• WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation
• Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
• VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment

Source: arXiv cs.CV | 2026-10-14