GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

Accurately perceiving dynamic environments is a fundamental task for autonomous driving and robotic systems. Existing methods inadequately utilize temporal information, relying mainly on local temporal interactions between adjacent frames and failing to leverage global sequence information effectively. To address this limitation, we investigate how to effectively aggregate global temporal features from temporal sequences, aiming to achieve occupancy representations that efficiently utilize global temporal information from historical observations. For this purpose, we propose a global temporal aggregation denoising network named GTAD, introducing a global temporal information aggregation framework as a new paradigm for holistic 3D scene understanding. Our method employs an in-model latent denoising network to aggregate local temporal features from the current moment and global temporal features from historical sequences. This approach enables the effective perception of both fine-grained temporal information from adjacent frames and global temporal patterns from historical observations. As a result, it provides a more coherent and comprehensive understanding of the environment. Extensive experiments on the nuScenes and Occ3D-nuScenes benchmark and ablation studies demonstrate the superiority of our method.

Authors

• Tianhao Li
• Yang Li
• Mengtian Li
• Yisheng Deng
• Weifeng Ge

Keywords

• Three-dimensional displays
• Aggregates
• Noise reduction
• Semantics
• Benchmark testing
• Intelligent robots
• Autonomous vehicles
• Denoising
• Temporal Aggregation
• Occupancy Prediction
• Paradigm Shift
• Global Features
• Temporal Features
• Temporal Information
• Global Patterns
• Global Information
• Temporal Sequence
• Historical Observations
• 3D Scene
• Adjacent Frames
• Scene Understanding
• Fine-grained Information
• Temporal Interactions
• Historical Sequence
• Total Loss
• Point Cloud
• Historical Features
• Semantic Segmentation
• Global Interaction
• 3D Object Detection
• Temporal Coding
• Local Assembly
• Voxel Grid
• Feature Alignment
• Historical Information
• Multi-view Images