# 3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning

arXiv: https://arxiv.org/abs/2510.03011 · HTML: https://mlsanity.com/paper/2510.03011/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## 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, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models](https://mlsanity.com/paper/2406.04806/) (2024)
- [EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning](https://mlsanity.com/paper/2309.11414/) (2023)
- [PointNet++ Grasping: Learning An End-to-end Spatial Grasp Generation Algorithm from Sparse Point Clouds](https://mlsanity.com/paper/2003.09644/) (2020)
- [Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models](https://mlsanity.com/paper/2412.19948/) (2024)
- [Denoise and Contrast for Category Agnostic Shape Completion](https://mlsanity.com/paper/2103.16671/) (2021)
- [PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting](https://mlsanity.com/paper/2211.06930/) (2022)
- [MaskPlanner: Learning-Based Object-Centric Motion Generation from 3D Point Clouds](https://mlsanity.com/paper/2502.18745/) (2025)

## Built on by (most cited first, 1 of 1)

- [MessyKitchens: Contact-rich object-level 3D scene reconstruction](https://mlsanity.com/paper/2603.16868/) (2026)

## Abstract (arXiv)

Diffusion models have shown strong potential for robot skill learning, yet their role in coverage path planning remains underexplored. In industrial surface processing (painting, polishing, spray coating), high coverage requires globally ordered, temporally coherent trajectories rather than stitching unordered local segments. We reformulate coverage path planning as conditional sequence generation and adopt a geometry-conditioned diffusion framework that synthesizes continuous trajectories directly from raw 3D point clouds. Our method produces temporally ordered trajectory chunks and avoids post-hoc heuristic ordering or stitching in prior learning-based methods via simple sequential concatenation, improving sequence-level consistency. A single shared policy generalizes across different geometries without category-specific architectures. Extensive benchmarks show substantial gains over prior learning-based baselines: 98.2% lower point-wise Chamfer Distance (lower is better), 97.0% lower jerk (smoother trajectories), and +67.5 percentage points overlapping surface coverage on average.