Diffusion-Based Generative Models for 3D Occupancy Prediction in 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.

Authors

• Yunshen Wang
• Yicheng Liu
• Tianyuan Yuan
• Yucheng Mao
• Yingshi Liang
• Xiuyu Yang
• Honggang Zhang
• Hang Zhao 0021

Keywords

• Solid modeling
• Visualization
• Three-dimensional displays
• Predictive models
• Diffusion models
• Planning
• Noise robustness
• Noise measurement
• Robotics and automation
• Autonomous vehicles
• Occupancy Prediction
• 3D Occupancy
• Prediction Accuracy
• 3D Structure
• Diffusion Model
• Noisy Data
• Visual Input
• Discrimination Method
• 3D Scene
• Realistic Predictions
• Occupancy Grid
• Incomplete Observations
• Underlying Data Distribution
• Training Set
• Denoising
• Bimodal
• Diffusion Process
• Hallucinations
• Point Cloud
• Model Discrimination
• Forward Process
• Prediction Quality
• Visual Encoding
• LiDAR Point Clouds
• Reversible Process
• Discrete Variables
• Noisy Regions
• Occupational Data
• Inference Step