PB-NBV: Efficient Projection-Based Next-Best-View Planning Framework for Reconstruction of Unknown Objects

2025-01-18

AI Summary

Existing ray-casting-based Next-Best-View (NBV) planning methods for online 3D reconstruction of unknown objects suffer from high computational overhead, hindering real-time deployment. This paper proposes an efficient NBV framework: first, it constructs a compact scene representation via voxel clustering and ellipsoidal geometric fitting—replacing expensive explicit ray casting; second, it introduces a projection-quality-driven viewpoint evaluation function coupled with a global partitioned sampling strategy to generate high-quality candidate views. In simulation, the method achieves the highest point cloud coverage while significantly reducing computation time. Real-world experiments on a robotic platform further validate its efficiency and practical deployability. The source code will be made publicly available.

Technology Category

• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Completely capturing the three-dimensional (3D) data of an object is essential in industrial and robotic applications. The task of next-best-view (NBV) planning is to calculate the next optimal viewpoint based on the current data, gradually achieving a complete 3D reconstruction of the object. However, many existing NBV planning algorithms incur heavy computational costs due to the extensive use of ray-casting. Specifically, this framework refits different types of voxel clusters into ellipsoids based on the voxel structure. Then, the next optimal viewpoint is selected from the candidate views using a projection-based viewpoint quality evaluation function in conjunction with a global partitioning strategy. This process replaces extensive ray-casting, significantly improving the computational efficiency. Comparison experiments in the simulation environment show that our framework achieves the highest point cloud coverage with low computational time compared to other frameworks. The real-world experiments also confirm the efficiency and feasibility of the framework. Our method will be made open source to benefit the community.

Problem

• 3D Reconstruction
• Optimal Angle Selection
• Industrial Robotics

Innovation

• Ellipsoid Modeling
• Next Best View
• Resource Efficiency