One Video, One World: Turning Monocular Video into Physical 4D Scenes

• URL: http://arxiv.org/abs/2606.31388v1
• Date: Tue, 30 Jun 2026 09:16:21 GMT
• Title: One Video, One World: Turning Monocular Video into Physical 4D Scenes
• Abstract summary: OVOW reconstructs emphinstance-level, simulation-ready 4D mesh scenes from a single monocular video.<n>We establish the first benchmark for emphstructured Video-to-4D evaluation, with metrics for geometric correctness, instance separation, and physical plausibility beyond visual fidelity.<n>OVOW attains the best overall layout and geometry accuracy and the lowest photometric and semantic error among all baselines.
• Score: 27.429882736058904
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce \textbf{OVOW}, the first training-free system that reconstructs \emph{instance-level, simulation-ready} 4D mesh scenes from a single monocular video. Recent 4D reconstruction achieves impressive rendering quality, but its outputs (\eg, implicit fields, Gaussian primitives, or point clouds) lack the watertight topology, instance separation, and standardized physical interfaces required by physics simulators and embodied AI. OVOW closes this gap with a four-stage pipeline: a vision-language model discovers, labels, and motion-classifies all instances; category-aware reconstruction yields per-instance meshes for rigid objects and topology-consistent mesh sequences for deformable ones; an iterative render-match-optimize procedure recovers metric scale and 6-DoF pose trajectories; and physics-grounded assembly enforces ground contact and inter-object support. Crucially, we model all motion, rigid and non-rigid, through direct vertex deformation without category-specific priors or skeleton rigging, producing watertight mesh scenes ready for downstream physics simulation and editing. We further establish the first benchmark for \emph{structured Video-to-4D} evaluation, with metrics for geometric correctness, instance separation, and physical plausibility beyond visual fidelity; the same pipeline doubles as a scalable engine for \emph{synthesizing} paired video-to-4D simulation data for future 4D world models and embodied AI. Across two synthetic benchmarks (static and 4D), OVOW attains the best overall layout and geometry accuracy and the lowest photometric and semantic error among all baselines, and on monocular video runs one to two orders of magnitude faster than the baselines, while downstream physics simulation confirms its physical stability.

Related papers

• SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation [50.175987640001644]
  We present SimWorlds: a multi-agent framework that produces dynamic, editable 4D scenes from text.<n>We also introduce 4DBuildBench, a benchmark for assessing both visual fidelity and physical consistency of the procedural dynamic 3D scenes.
  arXiv  Detail & Related papers  (2026-07-02T06:29:18Z)
• Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video [69.94904173314505]
  We propose Ground4D, a geometry-grounded framework built on two stages.<n>First, we reconstruct multi-view-consistent 3D geometry and camera poses from monocular video.<n>Second, we conduct geometry-consistency-aware refinement via dynamic Gaussian Splatting.
  arXiv  Detail & Related papers  (2026-06-27T09:27:42Z)
• High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians [38.0162622592412]
  We propose a novel system for the robust and accurate reconstruction of hands and objects from synchronized and calibrated multi-view videos.<n>Our pipeline achieves highly robust, artifact-free reconstruction, providing an efficient foundation for automated 4D asset generation.
  arXiv  Detail & Related papers  (2026-06-14T16:36:49Z)
• GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation [72.52773248997929]
  Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time.<n>We present GEM-4D, a geometry-grounded video world model that injects dense 4D correspondence supervision into the video generative backbone during training.<n>In inverse dynamics module converts correspondence-consistent video rollouts into executable robot trajectories, enabling direct deployment in both real-world and simulated manipulation.
  arXiv  Detail & Related papers  (2026-05-20T21:36:44Z)
• Resonance4D: Frequency-Domain Motion Supervision for Preset-Free Physical Parameter Learning in 4D Dynamic Physical Scene Simulation [53.141181758015186]
  We present Resonance4D, a physics-driven 4D dynamic simulation framework that couples 3D Gaussian Splatting with the Material Point Method.<n>Our key insight is that dynamic consistency can be enforced without dense temporal generation by jointly constraining motion in complementary domains.<n>We show that Resonance4D achieves strong physical fidelity and motion consistency while reducing peak GPU memory from over 35,GB to around 20,GB.
  arXiv  Detail & Related papers  (2026-04-02T13:00:22Z)
• Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion [43.09536633299663]
  We present textbfPhys4D, a pipeline for learning physics-consistent 4D world representations from video diffusion models.<n>We first perform robust geometry and motion representations through large-scale pseudo-supervised pretraining.<n>We then perform physics-grounded supervised fine-tuning using simulation bootstrap-generated data, enforcing temporally consistent 4D dynamics.
  arXiv  Detail & Related papers  (2026-03-03T20:01:43Z)
• Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis [53.48281548500864]
  Motion 3-to-4 is a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video.<n>Our model learns a compact motion latent representation and predicts per-frame trajectories to recover complete robustness, temporally coherent geometry.
  arXiv  Detail & Related papers  (2026-01-20T18:59:48Z)
• Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [79.06910348413861]
  We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image.<n>Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion.
  arXiv  Detail & Related papers  (2025-11-01T11:16:25Z)
• PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis [37.21119648359889]
  PhysGM is a feed-forward framework that jointly predicts a 3D Gaussian representation and its physical properties from a single image.<n>Our method effectively generates high-fidelity 4D simulations from a single image in one minute.
  arXiv  Detail & Related papers  (2025-08-19T15:10:30Z)
• DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors [75.83647027123119]
  We propose to learn the physical properties of a material field with video diffusion priors.<n>We then utilize a physics-based Material-Point-Method simulator to generate 4D content with realistic motions.
  arXiv  Detail & Related papers  (2024-06-03T16:05:25Z)

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.