# 3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space arXiv: https://arxiv.org/abs/2509.18676 · HTML: https://mlsanity.com/paper/2509.18676/ ## Key facts - Cited by 9 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 40 of its 45 references that are in the map. - First posted on arXiv 23 Sep 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, 30 of 40) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023) - [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016) - [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024) - [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023) - [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024) - [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022) - [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024) - [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025) - [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019) - [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021) - [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022) - [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023) - [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023) - [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025) - [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023) - [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024) - [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022) - [Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models](https://mlsanity.com/paper/2310.10639/) (2023) - [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023) - [GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators](https://mlsanity.com/paper/2309.13037/) (2023) - [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024) - [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](https://mlsanity.com/paper/2303.14158/) (2023) - [Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2306.17817/) (2023) - [Flow as the Cross-Domain Manipulation Interface](https://mlsanity.com/paper/2407.15208/) (2024) - [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023) - [Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2403.03890/) (2024) - [Video Generators are Robot Policies](https://mlsanity.com/paper/2508.00795/) (2025) - [General Flow as Foundation Affordance for Scalable Robot Learning](https://mlsanity.com/paper/2401.11439/) (2024) - [RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective](https://mlsanity.com/paper/2404.12281/) (2024) ## Built on by (most cited first, 9 of 9) - [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026) - [LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior](https://mlsanity.com/paper/2603.25399/) (2026) - [OMP: One-step Meanflow Policy with Directional Alignment](https://mlsanity.com/paper/2512.19347/) (2025) - [CUBic: Coordinated Unified Bimanual Perception and Control Framework](https://mlsanity.com/paper/2605.13452/) (2026) - [PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences](https://mlsanity.com/paper/2603.19762/) (2026) - [Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning](https://mlsanity.com/paper/2605.08511/) (2026) - [X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction](https://mlsanity.com/paper/2605.12162/) (2026) - [Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning](https://mlsanity.com/paper/2606.28813/) (2026) - [GeomVLA: Unifying Scene, Motion, and Action in 3D](https://mlsanity.com/paper/2609.13812/) (2026) ## Abstract (arXiv) Learning robust visuomotor policies that generalize across diverse objects and interaction dynamics remains a central challenge in robotic manipulation. Most existing approaches rely on direct observation-to-action mappings or compress perceptual inputs into global or object-centric features, which often overlook localized motion cues critical for precise and contact-rich manipulation. We present 3D Flow Diffusion Policy (3D FDP), a novel framework that leverages scene-level 3D flow as a structured intermediate representation to capture fine-grained local motion cues. Our approach predicts the temporal trajectories of sampled query points and conditions action generation on these interaction-aware flows, implemented jointly within a unified diffusion architecture. This design grounds manipulation in localized dynamics while enabling the policy to reason about broader scene-level consequences of actions. Extensive experiments on the MetaWorld benchmark show that 3D FDP achieves state-of-the-art performance across 50 tasks, particularly excelling on medium and hard settings. Beyond simulation, we validate our method on eight real-robot tasks, where it consistently outperforms prior baselines in contact-rich and non-prehensile scenarios. These results highlight 3D flow as a powerful structural prior for learning generalizable visuomotor policies, supporting the development of more robust and versatile robotic manipulation. Robot demonstrations, additional results, and code can be found at https://sites.google.com/view/3dfdp/home.