UniFuture: A 4D Driving World Model for Future Generation and Perception

Understand

We present UniFuture, a unified 4D Driving World Model designed to simulate the dynamic evolution of the 3D physical world.

• Unlike existing driving world models that focus solely on 2D pixel-level video generation (lacking geometry) or static perception (lacking temporal dynamics), our approach bridges appearance and geometry to construct a holistic 4D representation.
• Specifically, we treat future RGB images and depth maps as coupled projections of the same 4D reality and model them jointly within a single framework.
• To achieve this, we introduce a Dual-Latent Sharing (DLS) scheme, which maps visual and geometric modalities into a shared spatio-temporal latent space, implicitly entangling texture with structure.