CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations
This work addresses the need for efficient and self-contained occupancy world models in autonomous driving, offering a strong alternative to methods that depend on external foundation models.
CascadeOcc proposes a cascaded Vector Quantized (VQ) autoregressive framework for 3D occupancy world models in autonomous driving, achieving superior performance on 4D occupancy forecasting and motion planning benchmarks without relying on external modalities or large language models.
This letter proposes CascadeOcc, a novel occupancy world model that prioritizes intrinsic structural hierarchy over extrinsic auxiliary modalities for autonomous driving. Occupancy world models -- forecasting the future driving environment and planning the driving trajectory -- effectively bridge perception and planning, but current approaches often heavily rely on external modalities or large language models, failing to fully exploit the inherent structural potential of occupancy representations themselves. To enhance representational capacity for complex 3D scenes, we integrate a cascaded Vector Quantized (VQ) mechanism into an autoregressive framework. Following a coarse-to-fine principle, CascadeOcc progressively refines fine-grained details from global structures through a multi-scale architecture. Additionally, we incorporate a TimeMixer to capture multi-scale temporal dependencies, establishing a dual-hierarchy mechanism in both space and time. Experimental results on 4D occupancy forecasting and motion planning benchmarks demonstrate that CascadeOcc achieves superior performance among vision-centric approaches, validating that optimizing inherent representations is a powerful alternative to relying on external foundation models.