STCOcc: Sparse Spatial-Temporal Cascade Renovation for 3D Occupancy and Scene Flow Prediction

3D occupancy and scene flow offer a detailed and dynamic representation of 3D space, which is particularly critical for autonomous driving applications. Recognizing the sparsity and complexity of 3D space, previous vision-centric methods have employed implicit learning-based approaches to model spatial and temporal information. However, these approaches struggle to capture local details and diminish the model's spatial discriminative ability. To address these challenges, we propose a novel explicit state-based modeling method designed to leverage the occupied state to renovate the 3D features. Specifically, we propose a sparse occlusion-aware attention mechanism, integrated with a cascade refinement strategy, which accurately renovates 3D features with the guidance of occupied state information. Additionally, we introduce a novel sparse-based method to model long-term dynamic information, conserving computation while preserving spatial information. Compared to the previous state-of-the-art methods, our efficient explicit renovation strategy not only delivers superior performance in terms of RayIoU and MAVE for occupancy and scene flow prediction but also markedly reduces GPU memory usage during training, bringing it down to less than 8.7GB.