Learning 3D Persistent Embodied World Models

• URL: http://arxiv.org/abs/2505.05495v1
• Date: Mon, 05 May 2025 17:59:17 GMT
• Title: Learning 3D Persistent Embodied World Models
• Authors: Siyuan Zhou, Yilun Du, Yuncong Yang, Lei Han, Peihao Chen, Dit-Yan Yeung, Chuang Gan,
• Abstract summary: We introduce a new persistent embodied world model with an explicit memory of previously generated content.<n>During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent.<n>This generation is then aggregated into a persistent 3D map of the environment.
• Score: 84.40585374179037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing work has explored how to construct such world models using video models, they are often myopic in nature, without any memory of a scene not captured by currently observed images, preventing agents from making consistent long-horizon plans in complex environments where many parts of the scene are partially observed. We introduce a new persistent embodied world model with an explicit memory of previously generated content, enabling much more consistent long-horizon simulation. During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent. This generation is then aggregated into a persistent 3D map of the environment. By conditioning the video model on this 3D spatial map, we illustrate how this enables video world models to faithfully simulate both seen and unseen parts of the world. Finally, we illustrate the efficacy of such a world model in downstream embodied applications, enabling effective planning and policy learning.

Related papers

• Geometry-aware 4D Video Generation for Robot Manipulation [28.709339959536106]
  We propose a 4D video generation model that enforces multi-view 3D consistency of videos by supervising the model with cross-view pointmap alignment during training.<n>This geometric supervision enables the model to learn a shared 3D representation of the scene, allowing it to predict future video sequences from novel viewpoints.<n>Compared to existing baselines, our method produces more visually stable and spatially aligned predictions across multiple simulated and real-world robotic datasets.
  arXiv  Detail & Related papers  (2025-07-01T18:01:41Z)
• Video World Models with Long-term Spatial Memory [110.530715838396]
  We introduce a novel framework to enhance long-term consistency of video world models.<n>Our framework includes mechanisms to store and retrieve information from the long-term spatial memory.<n>Our evaluations show improved quality, consistency, and context length compared to relevant baselines.
  arXiv  Detail & Related papers  (2025-06-05T17:42:34Z)
• Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis [12.160537328404622]
  textttDRA-Ctrl provides new insights into reusing resource-intensive video models.<n>textttDRA-Ctrl lays foundation for future unified generative models across visual modalities.
  arXiv  Detail & Related papers  (2025-05-29T10:34:45Z)
• TesserAct: Learning 4D Embodied World Models [66.8519958275311]
  We learn a 4D world model by training on RGB-DN (RGB, Depth, and Normal) videos.<n>This not only surpasses traditional 2D models by incorporating detailed shape, configuration, and temporal changes into their predictions, but also allows us to effectively learn accurate inverse dynamic models for an embodied agent.
  arXiv  Detail & Related papers  (2025-04-29T17:59:30Z)
• PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model [23.768571323272152]
  PartRM is a novel 4D reconstruction framework that simultaneously models appearance, geometry, and part-level motion from multi-view images of a static object.<n>We introduce the PartDrag-4D dataset, providing multi-view observations of part-level dynamics across over 20,000 states.<n> Experimental results show that PartRM establishes a new state-of-the-art in part-level motion learning and can be applied in manipulation tasks in robotics.
  arXiv  Detail & Related papers  (2025-03-25T17:59:58Z)
• Aether: Geometric-Aware Unified World Modeling [49.33579903601599]
  Aether is a unified framework that enables geometry-aware reasoning in world models.<n>It achieves zero-shot generalization in both action following and reconstruction tasks.<n>We hope our work inspires the community to explore new frontiers in physically-reasonable world modeling.
  arXiv  Detail & Related papers  (2025-03-24T17:59:51Z)
• DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT [33.943125216555316]
  We present DrivingWorld, a GPT-style world model for autonomous driving.<n>We propose a next-state prediction strategy to model temporal coherence between consecutive frames.<n>We also propose a novel masking strategy and reweighting strategy for token prediction to mitigate long-term drifting issues.
  arXiv  Detail & Related papers  (2024-12-27T07:44:07Z)
• 3D-VLA: A 3D Vision-Language-Action Generative World Model [68.0388311799959]
  Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. We propose 3D-VLA by introducing a new family of embodied foundation models that seamlessly link 3D perception, reasoning, and action. Our experiments on held-in datasets demonstrate that 3D-VLA significantly improves the reasoning, multimodal generation, and planning capabilities in embodied environments.
  arXiv  Detail & Related papers  (2024-03-14T17:58:41Z)
• Persistent Nature: A Generative Model of Unbounded 3D Worlds [74.51149070418002]
  We present an extendable, planar scene layout grid that can be rendered from arbitrary camera poses via a 3D decoder and volume rendering. Based on this representation, we learn a generative world model solely from single-view internet photos. Our approach enables scene extrapolation beyond the fixed bounds of current 3D generative models, while also supporting a persistent, camera-independent world representation.
  arXiv  Detail & Related papers  (2023-03-23T17:59:40Z)

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.