UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning
This work addresses the challenge of autonomous driving by developing a model that integrates scene geometry, appearance, and dynamics, representing an incremental advancement in world modeling for this domain.
The paper tackles the problem of reliable planning in complex driving environments by proposing UniDWM, a unified driving world model that uses multifaceted representation learning to enable consistent reasoning across perception, prediction, and planning, with experiments showing effectiveness in trajectory planning, 4D reconstruction, and generation.
Achieving reliable and efficient planning in complex driving environments requires a model that can reason over the scene's geometry, appearance, and dynamics. We present UniDWM, a unified driving world model that advances autonomous driving through multifaceted representation learning. UniDWM constructs a structure- and dynamic-aware latent world representation that serves as a physically grounded state space, enabling consistent reasoning across perception, prediction, and planning. Specifically, a joint reconstruction pathway learns to recover the scene's structure, including geometry and visual texture, while a collaborative generation framework leverages a conditional diffusion transformer to forecast future world evolution within the latent space. Furthermore, we show that our UniDWM can be deemed as a variation of VAE, which provides theoretical guidance for the multifaceted representation learning. Extensive experiments demonstrate the effectiveness of UniDWM in trajectory planning, 4D reconstruction and generation, highlighting the potential of multifaceted world representations as a foundation for unified driving intelligence. The code will be publicly available at https://github.com/Say2L/UniDWM.