LiDAR-based 4D Occupancy Completion and Forecasting

Scene completion and forecasting are two popular perception problems in research for mobile agents like autonomous vehicles. Existing approaches treat the two problems in isolation, resulting in a separate perception of the two aspects. In this paper, we introduce a novel LiDAR perception task of Occupancy Completion and Forecasting (OCF) in the context of autonomous driving to unify these aspects into a cohesive framework. This task requires new algorithms to address three challenges altogether: (1) sparse-to-dense reconstruction, (2) partial-to-complete hallucination, and (3) 3D-to-4D prediction. To enable supervision and evaluation, we curate a large-scale dataset termed OCFBench from public autonomous driving datasets. We analyze the performance of closely related existing baselines and variants on our dataset. We envision that this research will inspire and call for further investigation in this evolving and crucial area of 4D perception. Our code for data curation and baseline implementation is available at https://github.com/ai4ce/Occ4cast.

Authors

• Xinhao Liu 0003
• Moonjun Gong
• Qi Fang
• Haoyu Xie
• Yiming Li 0003
• Hang Zhao 0021
• Chen Feng 0002

Keywords

• Training
• Point cloud compression
• Laser radar
• Codes
• Mobile agents
• Robot sensing systems
• Prediction algorithms
• Forecasting
• Autonomous vehicles
• Intelligent robots
• Hallucinations
• Data Curation
• Perceptual Task
• Isolation Problems
• Convolutional Layers
• Intersection Over Union
• Point Cloud
• Semantic Segmentation
• Multiple Tasks
• Semantic Labels
• Point Cloud Data
• Representation Of The Environment
• Dynamic Objects
• Trajectory Prediction
• Temporal Range
• Data Processing Pipeline
• Input Frames
• LiDAR Sensor
• Occupancy Grid
• Voxel Grid
• 2D Convolutional Layers
• Instance Labels
• Voxel Probability
• Ego-motion
• Model Architecture
• Moderate Performance
• Loss Function
• Test Frame