ScanDP: Generalizable 3D Scanning with Diffusion Policy

2026-03-11

AI Summary

This work proposes a data-efficient active 3D scanning framework that overcomes the limited generalization of existing reinforcement learning–based methods to unseen objects. By innovatively adopting a diffusion policy to mimic human scanning behavior, the approach integrates occupancy grid maps, spherical spatial representations, and hybrid path optimization to significantly enhance generalization and noise robustness without requiring large-scale training data. Experimental results demonstrate that the method achieves higher surface coverage and shorter scanning trajectories across a diverse set of previously unseen objects. Furthermore, real-world evaluations confirm its practical feasibility and stability in physical environments.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: 3D Computer Vision

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Learning-based 3D Scanning plays a crucial role in enabling efficient and accurate scanning of target objects. However, recent reinforcement learning-based methods often require large-scale training data and still struggle to generalize to unseen object categories.In this work, we propose a data-efficient 3D scanning framework that uses Diffusion Policy to imitate human-like scanning strategies. To enhance robustness and generalization, we adopt the Occupancy Grid Mapping instead of direct point cloud processing, offering improved noise resilience and handling of diverse object geometries. We also introduce a hybrid approach combining a sphere-based space representation with a path optimization procedure that ensures path safety and scanning efficiency. This approach addresses limitations in conventional imitation learning, such as redundant or unpredictable behavior. We evaluate our method on diverse unseen objects in both shape and scale. Ours achieves higher coverage and shorter paths than baselines, while remaining robust to sensor noise. We further confirm practical feasibility and stable operation in real-world execution.

Problem

• 3D Scanning
• Generalization
• Reinforcement Learning
• Imitation Learning
• Unseen Objects

Innovation

• Diffusion Policy
• Occupancy Grid Mapping
• 3D Scanning
• Generalization
• Path Optimization