# ScanDP: Generalizable 3D Scanning with Diffusion Policy

arXiv: https://arxiv.org/abs/2603.10390 · HTML: https://mlsanity.com/paper/2603.10390/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition](https://mlsanity.com/paper/2307.14535/) (2023)
- [Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation](https://mlsanity.com/paper/2308.07931/) (2023)
- [Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2403.03890/) (2024)
- [RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation](https://mlsanity.com/paper/2403.06341/) (2024)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction](https://mlsanity.com/paper/2402.16174/) (2024)
- [Next-Best View Policy for 3D Reconstruction](https://mlsanity.com/paper/2008.12664/) (2020)
- [ActiveRMAP: Radiance Field for Active Mapping And Planning](https://mlsanity.com/paper/2211.12656/) (2022)
- [GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy](https://mlsanity.com/paper/2410.17488/) (2024)
- [Geometrically Constrained Trajectory Optimization for Multicopters](https://mlsanity.com/paper/2103.00190/) (2021)
- [Neural Scene Representation for Locomotion on Structured Terrain](https://mlsanity.com/paper/2206.08077/) (2022)
- [DARE: Diffusion Policy for Autonomous Robot Exploration](https://mlsanity.com/paper/2410.16687/) (2024)
- [Bubble Planner: Planning High-speed Smooth Quadrotor Trajectories using Receding Corridors](https://mlsanity.com/paper/2202.12177/) (2022)
- [The Surface Edge Explorer (SEE): A measurement-direct approach to next best view planning](https://mlsanity.com/paper/2207.13684/) (2022)
- [Bubble Explorer: Fast UAV Exploration in Large-Scale and Cluttered 3D-Environments using Occlusion-Free Spheres](https://mlsanity.com/paper/2304.00852/) (2023)

## Abstract (arXiv)

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.