Diffusion models improve 3D occupancy prediction from visual inputs, enhancing accuracy and robustness in complex and occluded scenes, which benefits autonomous driving.
Accurately predicting 3D occupancy grids from visual inputs is critical for
autonomous driving, but current discriminative methods struggle with noisy
data, incomplete observations, and the complex structures inherent in 3D
scenes. In this work, we reframe 3D occupancy prediction as a generative
modeling task using diffusion models, which learn the underlying data
distribution and incorporate 3D scene priors. This approach enhances prediction
consistency, noise robustness, and better handles the intricacies of 3D spatial
structures. Our extensive experiments show that diffusion-based generative
models outperform state-of-the-art discriminative approaches, delivering more
realistic and accurate occupancy predictions, especially in occluded or
low-visibility regions. Moreover, the improved predictions significantly
benefit downstream planning tasks, highlighting the practical advantages of our
method for real-world autonomous driving applications.