MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence Modeling 

Our approach begins with a voxel-based semantic segmentation (SS) pretraining task, designed to explore the semantics and geometry of incomplete regions while acquiring transferable meta-knowledge. Using simulated cooperative perception datasets, we supervise the training of a single vehicle’s perception using the aggregated sensor data from multiple nearby connected autonomous vehicles (CAVs), generating richer and more comprehensive labels. This meta-knowledge is then adapted to the target domain through a dual-phase training strategy—without adding extra model parameters—ensuring efficient deployment. To further enhance the model’s ability to capture long-sequence relationships in 3D voxel grids, we integrate Mamba blocks with deformable convolution and large-kernel attention into the backbone network. Extensive experiments show that MetaSSC achieves state-of-the-art performance, surpassing competing models by a significant margin, while also reducing deployment costs.