Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation

• URL: http://arxiv.org/abs/2605.02757v1
• Date: Mon, 04 May 2026 15:57:07 GMT
• Title: Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
• Abstract summary: 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.
• Score: 39.90318150105298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited environmental diversity, resulting in weak real-world generalization. We present an efficient video augmentation framework that converts simulated VLA videos into realistic training videos while preserving task semantics and action trajectories. Our pipeline extracts structured conditions from simulation via video semantic segmentation and video captioning, rewrites captions to diversify environments, and uses a conditional video transfer model to synthesize realistic videos. To make augmentation practical at scale, we introduce a diffusion feature-reuse mechanism that reuses video tokens across adjacent timesteps to accelerate generation, and a coreset sampling strategy that identifies a compact, non-redundant subset for augmentation under limited computation. Extensive experiments on Robotwin 2.0, LIBERO, LIBERO-Plus, and a real robotic platform demonstrate consistent improvements. For example, our method improves RDT-1B by 8% on Robotwin 2.0, and boosts $π_0$ by 5.1% on the more challenging LIBERO-Plus benchmark. Code is available at: https://github.com/nanfangxiansheng/Seeing-Realism-from-Simulation.

Related papers

• GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments [63.222920701596564]
  Training embodied agents in the real world requires skilled operators and expensive hardware.<n> Simulation environments offer a compelling alternative by enabling large-scale, cost-effective data augmentation.<n>Fastly constructing high-fidelity simulation scenes with a minimal sim-to-real gap has become a critical objective in robot learning.
  arXiv  Detail & Related papers  (2026-06-16T05:00:42Z)
• GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning [55.272458304179025]
  GS-Playground is a multi-modal simulation framework designed to accelerate end-to-end perceptual learning.<n>Our system achieves a breakthrough throughput of 104 FPS at 640x480 resolution, significantly lowering the barrier for large-scale visual RL.
  arXiv  Detail & Related papers  (2026-04-28T10:05:39Z)
• ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation [90.4702774169675]
  We propose a novel hybrid approach called Compositional Simulation, which combines classical simulation and neural simulation.<n>Our approach utilizes a closed-loop real-sim-real data augmentation pipeline, leveraging a small amount of real-world data.<n>We train a neural simulator to transform classical simulation videos into real-world representations, improving the accuracy of policy models trained in real-world environments.
  arXiv  Detail & Related papers  (2026-04-13T12:25:45Z)
• CRAFT: Video Diffusion for Bimanual Robot Data Generation [3.1921574296387916]
  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.
  arXiv  Detail & Related papers  (2026-04-04T02:36:54Z)
• DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control [16.562259973551786]
  We introduce DiT4DiT, an end-to-end Video-Action Model that couples a video Diffusion Transformer with an action Diffusion Transformer.<n>Instead of relying on reconstructed future frames, DiT4DiT extracts intermediate denoising features from the video generation process.<n>It achieves state-of-the-art results, reaching average success rates of 98.6% on LIBERO and 50.8% on RoboCasa GR1.
  arXiv  Detail & Related papers  (2026-03-11T06:03:53Z)
• ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection [27.18540416686717]
  ExoGS is a robot-free 4D Real-to-Sim-to-Real framework.<n>It captures both static environments and dynamic interactions in the real world and transfers them seamlessly to a simulated environment.<n>It provides a new solution for scalable manipulation data collection and policy learning.
  arXiv  Detail & Related papers  (2026-01-26T16:04:12Z)
• 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)
• SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding [64.86119288520419]
  multimodal language models struggle with spatial reasoning across time and space.<n>We present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators.<n>Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks.
  arXiv  Detail & Related papers  (2025-11-06T18:53:31Z)
• EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer [35.27100635173712]
  Vision-language-action (VLA) models increasingly rely on diverse training data to achieve robust generalization.<n>We propose Embodied Manipulation Media Adaptation (EMMA), a VLA policy enhancement framework that integrates a generative data engine with an effective training pipeline.<n>DreamTransfer enables text-controlled visual editing of robot videos, transforming foreground, background, and lighting conditions without compromising 3D structure or geometrical plausibility.<n>AdaMix is a hard-sample-aware training strategy that dynamically reweights training batches to focus optimization on perceptually or kinematically challenging samples.
  arXiv  Detail & Related papers  (2025-09-26T14:34:44Z)
• 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)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)

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.