Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model

• URL: http://arxiv.org/abs/2604.03181v1
• Date: Fri, 03 Apr 2026 16:57:06 GMT
• Title: Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model
• Abstract summary: We introduce MV-VDP, a multiview video policy that jointly models 3D state of environment.<n> Extensive experiments show that MV-VDP enables data-efficient, robust, generalizable, and interpretable manipulation.<n> Experiments on Meta-World and real-world robotic platforms demonstrate that MV-VDP consistently outperforms video-prediction-based, 3D-based, and vision--language--action models.
• Score: 43.80385042752741
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained on static image--text pairs, resulting in high data requirements and limited understanding of environment dynamics. To address this, we introduce MV-VDP, a multi-view video diffusion policy that jointly models the 3D spatio-temporal state of the environment. The core idea is to simultaneously predict multi-view heatmap videos and RGB videos, which 1) align the representation format of video pretraining with action finetuning, and 2) specify not only what actions the robot should take, but also how the environment is expected to evolve in response to those actions. Extensive experiments show that MV-VDP enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and without additional pretraining, MV-VDP successfully performs complex real-world tasks, demonstrates strong robustness across a range of model hyperparameters, generalizes to out-of-distribution settings, and predicts realistic future videos. Experiments on Meta-World and real-world robotic platforms demonstrate that MV-VDP consistently outperforms video-prediction--based, 3D-based, and vision--language--action models, establishing a new state of the art in data-efficient multi-task manipulation.

Related papers

• DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning [28.673173377342593]
  General robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions.<n>DeVA is a Decoupled Video-Action model with specialized video and action experts, multi-level feature transfer, and physically guidance.<n> Experiments on both simulation benchmarks and real-world deployment demonstrate strong performance with limited data, faster convergence than a unified architecture, and clear performance gains from physical guidance.
  arXiv  Detail & Related papers  (2026-07-27T08:37:35Z)
• Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation [88.94027963091206]
  We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence.<n>It predicts physically grounded future visual trajectories from current observations across robotic manipulation, autonomous driving, indoor navigation, and human-to-robot transfer.
  arXiv  Detail & Related papers  (2026-06-15T17:52:31Z)
• From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [71.22409934108924]
  Human videos are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation.<n>This survey provides a unified view of how human videos are transformed into effective knowledge for Vision-Language-Action (VLA) models.<n>We highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency.
  arXiv  Detail & Related papers  (2026-05-18T06:19:16Z)
• GigaWorld-Policy: An Efficient Action-Centered World--Action Model [50.107640832046464]
  GigaWorld-Policy is an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation.<n> Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus.
  arXiv  Detail & Related papers  (2026-03-18T00:52:02Z)
• MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model [83.12400850233034]
  Human-Object Interaction (HOI) video reenactment with realistic motion remains a frontier in digital human creation.<n>We propose MVHOI, a two-stage HOI video reenactment framework that bridges multi-view reference conditions and video foundation models.<n>Our framework shows superior performance in generating long-duration HOI videos with intricate object manipulations.
  arXiv  Detail & Related papers  (2026-03-16T00:43:38Z)
• Causal World Modeling for Robot Control [56.31803788587547]
  Video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics.<n>We introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously.<n>We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations.
  arXiv  Detail & Related papers  (2026-01-29T17:07:43Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation [52.136378691610524]
  We present DynaRend, a representation learning framework that learns 3D-aware and dynamics-informed triplane features.<n>By pretraining on multi-view RGB-D video data, DynaRend jointly captures spatial geometry, future dynamics, and task semantics in a unified triplane representation.<n>We evaluate DynaRend on two challenging benchmarks, RLBench and Colosseum, demonstrating substantial improvements in policy success rate, generalization to environmental perturbations, and real-world applicability across diverse manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-28T10:17:11Z)
• 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)
• Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations [19.45821593625599]
  Video diffusion models (VDMs) demonstrate the ability to predict future frames and showcase a strong understanding of physical world.<n>We propose the Video Prediction Policy (VPP), which learns implicit inverse dynamics model conditioned on predicted future representations inside VDMs.<n>VPP achieves a 18.6% relative improvement on the Calvin ABC-D generalization benchmark compared to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2024-12-19T12:48:40Z)

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.