FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy
Not on the map. Why?
Abstract (arXiv)
We address the problem of goal-directed cloth manipulation, a challenging task due to the deformability of cloth. Our insight is that optical flow, a technique normally used for motion estimation in video, can also provide an effective representation for corresponding cloth poses across observation and goal images. We introduce FabricFlowNet (FFN), a cloth manipulation policy that leverages flow as both an input and as an action representation to improve performance. FabricFlowNet also elegantly switches between bimanual and single-arm actions based on the desired goal. We show that FabricFlowNet significantly outperforms state-of-the-art model-free and model-based cloth manipulation policies that take image input. We also present real-world experiments on a bimanual system, demonstrating effective sim-to-real transfer. Finally, we show that our method generalizes when trained on a single square cloth to other cloth shapes, such as T-shirts and rectangular cloths. Video and other supplementary materials are available at: https://sites.google.com/view/fabricflownet.
Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 10 Nov 2021.
Builds on
24 of 47 references.
References · 24
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
- 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
- 2020SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulationcited by 118
- 2018Zero-Shot Visual Imitationcited by 114
- 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
- 2021FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfoldingcited by 80
- 2020Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networkscited by 77
- 2019Learning to Manipulate Deformable Objects without Demonstrationscited by 76
- 2020Learning Predictive Representations for Deformable Objects Using Contrastive Estimationcited by 72
- 2020Deep Imitation Learning for Bimanual Robotic Manipulationcited by 49
12 more
- 2021Tactile-RL for Insertion: Generalization to Objects of Unknown Geometrycited by 45
- 2019Efficient Bimanual Manipulation Using Learned Task Schemascited by 44
- 2019Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisorcited by 44
- 2021GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completioncited by 41
- 2020VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulationcited by 40
- 2019Dynamic Cloth Manipulation with Deep Reinforcement Learningcited by 26
- 2020Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulationcited by 25
- 2020Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experiencecited by 24
- 2020FlowControl: Optical Flow Based Visual Servoingcited by 15
- 2019A Grasping-centered Analysis for Cloth Manipulationcited by 14
- 2019Motion Perception in Reinforcement Learning with Dynamic Objectscited by 13
- 2020Intrinsic Motivation for Encouraging Synergistic Behaviorcited by 13
Built on by
Citing papers per year: 2022: 10; 2023: 11; 2024: 14; 2025: 11; 2026: 8.
54 papers.
Sort:
By area:
- 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 206
- 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
- 2024General Flow as Foundation Affordance for Scalable Robot Learningcited by 80
- 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 74
- 2023Multi-Stage Cable Routing through Hierarchical Imitation Learningcited by 59
- 2022SpeedFolding: Learning Efficient Bimanual Folding of Garmentscited by 51
- 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
- 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
- 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
- 2022Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulationcited by 32
- 2023Learning Foresightful Dense Visual Affordance for Deformable Object Manipulationcited by 25
- 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physicscited by 23
38 more
- 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondencecited by 22
- 2024VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulationcited by 21
- 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
- 2025Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flowcited by 21
- 2024Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloningcited by 19
- 2022DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulationcited by 18
- 2024ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projectioncited by 16
- 2024Neural Eulerian Scene Flow Fieldscited by 14
- 2023UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Foldingcited by 13
- 2025Normalizing Flows are Capable Models for Continuous Controlcited by 13
- 2022EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamicscited by 10
- 2023Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attentioncited by 10
- 2024NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulationcited by 10
- 2022Autonomously Untangling Long Cablescited by 9
- 2025GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulationcited by 9
- 2022Learning Fabric Manipulation in the Real World with Human Videoscited by 7
- 2024SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policycited by 7
- 2022Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Researchcited by 6
- 2023DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physicscited by 6
- 2022Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactionscited by 5
- 2023QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulationcited by 5
- 2024TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approachcited by 5
- 2024General-purpose Clothes Manipulation with Semantic Keypointscited by 5
- 2026SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reusecited by 5
- 2025BiFold: Bimanual Cloth Folding with Language Guidancecited by 4
- 2025D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentationcited by 4
- 2025One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenescited by 3
- 2023Push Past Green: Learning to Look Behind Plant Foliage by Moving Itcited by 2
- 2024Non-rigid Relative Placement through 3D Dense Diffusioncited by 2
- 2023PlaNet-ClothPick: Effective Fabric Flattening Based on Latent Dynamic Planningcited by 1
- 2025CLASP: General-Purpose Clothes Manipulation with Semantic Keypointscited by 1
- 2025ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentationcited by 1
- 2026GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoningcited by 1
- 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulationcited by 1
- 2024DRAPER: Towards a Robust Robot Deployment and Reliable Evaluation for Quasi-Static Pick-and-Place Cloth-Shaping Neural Controllerscited by 0
- 2024UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registrationcited by 0
- 2025Beyond Static Perception: Integrating Temporal Context into VLMs for Cloth Foldingcited by 0
- 2025RoboPearls: Editable Video Simulation for Robot Manipulationcited by 0
50 most cited of 54 All 54 (JSON)
- 2026DSDyn-VLA: A Dual-Stream Dynamic Manipulation Framework with Motion Perception, Future Awareness, and Realtime Correction30 Sep 2026
- 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation2 Jun 2026
- 2026DexKnot: Generalizable Visuomotor Policy Learning for Dexterous Bag-Knotting Manipulation7 Mar 2026
- 2026GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning4 Mar 2026
- 2026SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse4 Mar 2026
- 2026Disentangling perception and reasoning for improving data efficiency in learning cloth manipulation without demonstrations29 Jan 2026
- 2026TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement28 Jan 2026
- 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation7 Jan 2026
- 2025Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow31 Dec 2025
- 2025ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation23 Sep 2025
- 2025CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints26 Jul 2025
- 2025RoboPearls: Editable Video Simulation for Robot Manipulation28 Jun 2025
38 more
- 2025Normalizing Flows are Capable Models for Continuous Control29 May 2025
- 2025Beyond Static Perception: Integrating Temporal Context into VLMs for Cloth Folding12 May 2025
- 2025D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation8 May 2025
- 2025GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation12 Mar 2025
- 2025One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes3 Mar 2025
- 2025BiFold: Bimanual Cloth Folding with Language Guidance27 Jan 2025
- 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation24 Jan 2025
- 2024UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration30 Oct 2024
- 2024Non-rigid Relative Placement through 3D Dense Diffusion25 Oct 2024
- 2024Neural Eulerian Scene Flow Fields2 Oct 2024
- 2024DRAPER: Towards a Robust Robot Deployment and Reliable Evaluation for Quasi-Static Pick-and-Place Cloth-Shaping Neural Controllers23 Sep 2024
- 2024General-purpose Clothes Manipulation with Semantic Keypoints15 Aug 2024
- 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations8 Aug 2024
- 2024VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulation4 Jul 2024
- 2024TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approach3 Jul 2024
- 2024Render and Diffuse: Aligning Image and Action Spaces for Diffusion-based Behaviour Cloning28 May 2024
- 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence11 May 2024
- 2024ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projection6 May 2024
- 2024SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy15 Mar 2024
- 2024NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation13 Mar 2024
- 2024General Flow as Foundation Affordance for Scalable Robot Learning21 Jan 2024
- 2023DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics11 Dec 2023
- 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation2 Nov 2023
- 2023UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Folding2 Nov 2023
- 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation24 Oct 2023
- 2023Multi-Stage Cable Routing through Hierarchical Imitation Learning18 Jul 2023
- 2023Push Past Green: Learning to Look Behind Plant Foliage by Moving It6 Jul 2023
- 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics27 Mar 2023
- 2023QDP: Learning to Sequentially Optimise Quasi-Static and Dynamic Manipulation Primitives for Robotic Cloth Manipulation23 Mar 2023
- 2023Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation20 Mar 2023
- 2023PlaNet-ClothPick: Effective Fabric Flattening Based on Latent Dynamic Planning2 Mar 2023
- 2023Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention8 Jan 2023
- 2022Learning Fabric Manipulation in the Real World with Human Videos5 Nov 2022
- 2022EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamics19 Sep 2022
- 2022SpeedFolding: Learning Efficient Bimanual Folding of Garments22 Aug 2022
- 2022Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactions11 Aug 2022
- 2022Autonomously Untangling Long Cables16 Jul 2022
- 2022DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation5 Jul 2022
50 newest of 54 All 54 (JSON)
- 2023Multi-Stage Cable Routing through Hierarchical Imitation Learningcited by 59
- 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
- 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulationcited by 21
- 2025D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentationcited by 4
- 2025ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentationcited by 1
- 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulationcited by 1
- 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation2 Jun 2026
- 2025ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation23 Sep 2025
- 2025D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation8 May 2025
- 2025SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation24 Jan 2025
- 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations8 Aug 2024
- 2023Multi-Stage Cable Routing through Hierarchical Imitation Learning18 Jul 2023
- 2023RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulationcited by 206
- 2022FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objectscited by 91
- 2024General Flow as Foundation Affordance for Scalable Robot Learningcited by 80
- 2022SpeedFolding: Learning Efficient Bimanual Folding of Garmentscited by 51
- 2022DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Toolscited by 44
- 2023EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulationcited by 37
- 2022Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulationcited by 32
- 2023Learning Foresightful Dense Visual Affordance for Deformable Object Manipulationcited by 25
- 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physicscited by 23
- 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondencecited by 22
- 2024VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulationcited by 21
- 2025Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flowcited by 21
12 most cited of 42 All 42 (JSON)
- 2026GarmentPile++: Affordance-Driven Cluttered Garments Retrieval with Vision-Language Reasoning4 Mar 2026
- 2026Disentangling perception and reasoning for improving data efficiency in learning cloth manipulation without demonstrations29 Jan 2026
- 2025Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow31 Dec 2025
- 2025CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints26 Jul 2025
- 2025RoboPearls: Editable Video Simulation for Robot Manipulation28 Jun 2025
- 2025Normalizing Flows are Capable Models for Continuous Control29 May 2025
- 2025Beyond Static Perception: Integrating Temporal Context into VLMs for Cloth Folding12 May 2025
- 2025GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation12 Mar 2025
- 2025One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes3 Mar 2025
- 2025BiFold: Bimanual Cloth Folding with Language Guidance27 Jan 2025
- 2024UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration30 Oct 2024
- 2024Non-rigid Relative Placement through 3D Dense Diffusion25 Oct 2024
12 newest of 42 All 42 (JSON)