DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle’s surroundings. However, such systems struggle to perceive occluded areas and gaps in the scene due to the sparsity of these point clouds and their lack of semantics. To address these challenges, Semantic Scene Completion (SSC) jointly predicts unobserved geometry and semantics in the scene given raw LiDAR measurements, aiming for a more complete scene representation. Building on promising results of diffusion models in image generation and super-resolution tasks, we propose their extension to SSC by implementing the noising and denoising diffusion processes in the point and semantic spaces individually. To control the generation, we employ semantic LiDAR point clouds as conditional input and design local and global regularization losses to stabilize the denoising process. We evaluate our approach on autonomous driving datasets, and it achieves state-of-the-art performance for SSC, surpassing most existing methods.

Authors

• Helin Cao
• Sven Behnke

Keywords

• Point cloud compression
• Laser radar
• Three-dimensional displays
• Semantics
• Noise reduction
• Superresolution
• Diffusion models
• Sensor systems
• Sensors
• Autonomous vehicles
• LiDAR Scans
• Diffusion Probabilistic Models
• Diffusion Process
• Point Cloud
• Diffusion Model
• Semantic Space
• LiDAR Sensor
• Scene Representation
• LiDAR Point Clouds
• Sparse Point Cloud
• High-quality
• Gaussian Noise
• Object Detection
• Spatial Domain
• Semantic Segmentation
• Noise Intensity
• Semantic Labels
• Lidar Data
• Partial Observation
• Semantic Domain
• Noise Injection
• Pure Noise
• Raw Point
• Raw Point Cloud
• Part Of The Input
• Reduce Resource Consumption
• 3D LiDAR
• Occluded Regions
• Part Of The Scene