Camera-Based Synthetic Completion of Point Clouds Captured with Quadruped Robot
LiDAR-based perception systems commonly used in mobile robots often struggle to accurately capture transparent or reflective surfaces such as glass, leading to incomplete point clouds and degraded understanding of the scene. This paper presents a camera-based synthetic point cloud completion method designed to address these limitations. The proposed approach integrates RGB images with LiDAR measurements using a quadruped robot equipped with synchronized sensors. A deep learning model based on YOLOv26 is trained to detect and segment window regions in camera images. The resulting semantic information is projected onto corresponding LiDAR data to identify areas with missing geometry. For each detected region, planar surfaces are estimated and synthetic points are generated within these boundaries to reconstruct the missing structures. Experimental evaluation conducted on a real-world dataset demonstrates that the method significantly improves the completeness and consistency of point clouds, particularly in areas containing glass surfaces. The enhanced maps provide more accurate 3D representations, which can improve navigation, obstacle avoidance, and path planning in robotics.