# Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow

arXiv: https://arxiv.org/abs/2512.24766 · HTML: https://mlsanity.com/paper/2512.24766/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 86 of its 91 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Builds on (most cited first, 30 of 86)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models](https://mlsanity.com/paper/2310.10639/) (2023)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation](https://mlsanity.com/paper/2112.05124/) (2021)
- [AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains](https://mlsanity.com/paper/2212.08333/) (2022)

## Built on by (most cited first, 25 of 25)

- [PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation](https://mlsanity.com/paper/2601.03782/) (2026)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data](https://mlsanity.com/paper/2607.08436/) (2026)
- [Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation](https://mlsanity.com/paper/2602.15828/) (2026)
- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [Point Tracking Improves World Action Models](https://mlsanity.com/paper/2605.23856/) (2026)
- [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model](https://mlsanity.com/paper/2605.31234/) (2026)
- [MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction](https://mlsanity.com/paper/2606.18558/) (2026)
- [μ0: A Scalable 3D Interaction-Trace World Model](https://mlsanity.com/paper/2606.13769/) (2026)
- [PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos](https://mlsanity.com/paper/2603.25539/) (2026)
- [CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL](https://mlsanity.com/paper/2605.14274/) (2026)
- [Articulated Object Reconstruction from Rest-State Observation](https://mlsanity.com/paper/2607.27749/) (2026)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal](https://mlsanity.com/paper/2608.20107/) (2026)
- [LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation](https://mlsanity.com/paper/2604.08475/) (2026)
- [X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction](https://mlsanity.com/paper/2605.12162/) (2026)
- [Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?](https://mlsanity.com/paper/2606.04811/) (2026)
- [DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents](https://mlsanity.com/paper/2608.00486/) (2026)
- [IM-ENGINE: Image Editing for Embodied Data Generation](https://mlsanity.com/paper/2609.06279/) (2026)
- [Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation](https://mlsanity.com/paper/2609.19137/) (2026)
- [XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation](https://mlsanity.com/paper/2610.03516/) (2026)
- [Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution](https://mlsanity.com/paper/2610.04152/) (2026)
- [CASTER: Formalizing Zero-Shot Manipulation from Synthetic Videos as Constrained Optimization](https://mlsanity.com/paper/2610.12567/) (2026)

## Abstract (arXiv)

Generative video modeling has emerged as a compelling tool to zero-shot reason about plausible physical interactions for open-world manipulation. Yet, it remains a challenge to translate such human-led motions into the low-level actions demanded by robotic systems. We observe that given an initial image and task instruction, these models excel at synthesizing sensible object motions. Thus, we introduce Dream2Flow, a framework that bridges video generation and robotic control through 3D object flow as an intermediate representation. Our method reconstructs 3D object motions from generated videos and formulates manipulation as object trajectory tracking. By separating the state changes from the actuators that realize those changes, Dream2Flow overcomes the embodiment gap and enables zero-shot guidance from pre-trained video models to manipulate objects of diverse categories-including rigid, articulated, deformable, and granular. Through trajectory optimization or reinforcement learning, Dream2Flow converts reconstructed 3D object flow into executable low-level commands without task-specific demonstrations. Simulation and real-world experiments highlight 3D object flow as a general and scalable interface for adapting video generation models to open-world robotic manipulation. Videos and visualizations are available at https://dream2flow.github.io/.