CRAFT: Video Diffusion for Bimanual Robot Data Generation

• URL: http://arxiv.org/abs/2604.03552v1
• Date: Sat, 04 Apr 2026 02:36:54 GMT
• Title: CRAFT: Video Diffusion for Bimanual Robot Data Generation
• Abstract summary: Bimanual robot learning from demonstrations is fundamentally limited by the cost and narrow visual diversity of real-world data.<n>We present Canny-guided Robot Data Generation using Video Diffusion Transformers (CRAFT)<n>CRAFT synthesizes temporally coherent manipulation videos while producing action labels.
• Score: 3.1921574296387916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bimanual robot learning from demonstrations is fundamentally limited by the cost and narrow visual diversity of real-world data, which constrains policy robustness across viewpoints, object configurations, and embodiments. We present Canny-guided Robot Data Generation using Video Diffusion Transformers (CRAFT), a video diffusion-based framework for scalable bimanual demonstration generation that synthesizes temporally coherent manipulation videos while producing action labels. By conditioning video diffusion on edge-based structural cues extracted from simulator-generated trajectories, CRAFT produces physically plausible trajectory variations and supports a unified augmentation pipeline spanning object pose changes, camera viewpoints, lighting and background variations, cross-embodiment transfer, and multi-view synthesis. We leverage a pre-trained video diffusion model to convert simulated videos, along with action labels from the simulation trajectories, into action-consistent demonstrations. Starting from only a few real-world demonstrations, CRAFT generates a large, visually diverse set of photorealistic training data, bypassing the need to replay demonstrations on the real robot (Sim2Real). Across simulated and real-world bimanual tasks, CRAFT improves success rates over existing augmentation strategies and straightforward data scaling, demonstrating that diffusion-based video generation can substantially expand demonstration diversity and improve generalization for dual-arm manipulation tasks. Our project website is available at: https://craftaug.github.io/

Related papers

• Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation [39.90318150105298]
  Vision-language--action (VLA) models typically rely on large-scale real-world videos.<n>We present an efficient video augmentation framework that converts simulated VLA videos into realistic training videos.
  arXiv  Detail & Related papers  (2026-05-04T15:57:07Z)
• DRAW2ACT: Turning Depth-Encoded Trajectories into Robotic Demonstration Videos [24.681248200255975]
  Video models provide powerful real-world simulators for embodied AI but remain limited in controllability for robotic manipulation.<n>We present DRAW2ACT, a trajectory-conditioned video generation framework that extracts multiple representations from the input trajectory.<n>We show that DRAW2ACT achieves superior visual fidelity and consistency while yielding higher manipulation success rates compared to existing baselines.
  arXiv  Detail & Related papers  (2025-12-16T09:11:36Z)
• AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis [33.90053396451562]
  We introduce AnchorDream, an embodiment-aware world model that repurposes pretrained video diffusion models for robot data synthesis.<n>Our method scales them into large, diverse, high-quality datasets without requiring explicit environment modeling.<n>Experiments show that the generated data leads to consistent improvements in downstream policy learning, with relative gains of 36.4% in simulator benchmarks and nearly double performance in real-world studies.
  arXiv  Detail & Related papers  (2025-12-12T18:59:45Z)
• GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning [79.68241687396603]
  We propose GenFlowRL, which derives shaped rewards from generated flow trained from diverse cross-embodiment datasets.<n>Experiments on 10 manipulation tasks, both in simulation and real-world cross-embodiment evaluations, demonstrate that GenFlowRL effectively leverages manipulation features extracted from generated object-centric flow.
  arXiv  Detail & Related papers  (2025-08-14T20:19:20Z)
• Vidar: Embodied Video Diffusion Model for Generalist Manipulation [28.216910600346512]
  Vidar is a prior-driven, low-shot adaptation paradigm that replaces most embodiment-specific data with transferable video priors.<n>Our results suggest a scalable recipe for "one prior, many embodiments": strong, inexpensive video priors + minimal on-robot alignment.
  arXiv  Detail & Related papers  (2025-07-17T08:31:55Z)
• Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations [19.28925489415787]
  RIGVid enables robots to perform complex manipulation tasks by imitating AI-generated videos.<n>A video diffusion model generates potential demonstration videos, and a vision-language model automatically filters out results that do not follow the command.<n>A 6D pose tracker then extracts object trajectories from the video, and the trajectories are retargeted to the robot in an embodiment-agnostic fashion.
  arXiv  Detail & Related papers  (2025-07-01T17:39:59Z)
• RoboPearls: Editable Video Simulation for Robot Manipulation [81.18434338506621]
  RoboPearls is an editable video simulation framework for robotic manipulation.<n>Built on 3D Gaussian Splatting (3DGS), RoboPearls enables the construction of photo-realistic, view-consistent simulations.<n>We conduct extensive experiments on multiple datasets and scenes, including RLBench, COLOSSEUM, Ego4D, Open X-Embodiment, and a real-world robot.
  arXiv  Detail & Related papers  (2025-06-28T05:03:31Z)
• VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation [53.63540587160549]
  VidBot is a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos.<n> VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.
  arXiv  Detail & Related papers  (2025-03-10T10:04:58Z)
• Pre-Trained Video Generative Models as World Simulators [59.546627730477454]
  We propose Dynamic World Simulation (DWS) to transform pre-trained video generative models into controllable world simulators.<n>To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module.<n> Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models.
  arXiv  Detail & Related papers  (2025-02-10T14:49:09Z)
• Video Creation by Demonstration [59.389591010842636]
  We present $delta$-Diffusion, a self-supervised training approach that learns from unlabeled videos by conditional future frame prediction.<n>By leveraging a video foundation model with an appearance bottleneck design on top, we extract action latents from demonstration videos for conditioning the generation process.<n> Empirically, $delta$-Diffusion outperforms related baselines in terms of both human preference and large-scale machine evaluations.
  arXiv  Detail & Related papers  (2024-12-12T18:41:20Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.