ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions

• URL: http://arxiv.org/abs/2609.15392v1
• Date: Mon, 14 Sep 2026 11:19:25 GMT
• Title: ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions
• Abstract summary: We present a unified framework for generating physically consistent 3D scenes from text, with directly executable in Unreal Engine.<n>We use the emphEvolutive Scene Graph (ESG), which specifies entities with physical attributes, spatial relations, and event-driven timelines in a machine-checkable form.
• Score: 19.29011683959245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such static configurations. Generating dynamic scenes from natural language is fundamentally challenging: it requires joint reasoning over scene structure, temporal evolution, and physical feasibility, while ensuring reliable execution in modern physics engines. We present a unified framework for generating physically consistent dynamic 3D scenes from text, with outputs directly executable in Unreal Engine. Central to our approach is the \emph{Evolutive Scene Graph} (ESG), which specifies entities with physical attributes, spatial relations, and event-driven timelines in a machine-checkable form. Given a prompt, a large language model constructs and validates a complete ESG; spatial layouts are grounded via energy-minimized gradient optimization; timeline-constrained physical parameters are then optimized through differentiable simulation to satisfy user-specified events; and the resulting scene is compiled into an engine-executable class. Experiments on 10 scenes across three complexity levels show that our method achieves $16.4/18$ mean event completion, outperforming Scene Language, the strongest engine-executable baseline (SimWorld), and our ablation without physical optimization by a clear margin in event completion and parameter accuracy.

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)
• PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation [75.9028457575434]
  Generating 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning.<n>Here, we introduce PhyScene3D, a framework that reformulates generation as a Human-Mimetic Constructive Process.<n>Experiments demonstrate that PhyScene3D outperforms state-of-the-art approaches in both semantic accuracy and physical validity.
  arXiv  Detail & Related papers  (2026-06-01T03:56:32Z)
• Physical Simulator In-the-Loop Video Generation [96.87054314612142]
  Physical Simulator In-the-loop Video Generation (PSIVG) is a novel framework that integrates a physical simulator into the video diffusion process.<n>PSIVG produces videos that better adhere to real-world physics while preserving visual quality and diversity.
  arXiv  Detail & Related papers  (2026-03-06T15:48:25Z)
• SceMoS: Scene-Aware 3D Human Motion Synthesis by Planning with Geometry-Grounded Tokens [89.05195827071582]
  SceMoS is a scene-aware motion synthesis framework.<n>It disentangles global planning from local execution using lightweight 2D cues.<n>SceMoS achieves state-of-the-art motion realism and contact accuracy on the TRUMANS benchmark.
  arXiv  Detail & Related papers  (2026-02-24T02:09:12Z)
• PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement [89.35154754765502]
  PhyScensis is an agent-based framework powered by a physics engine to produce physically plausible scene configurations.<n>Our framework preserves strong controllability over fine-grained textual descriptions and numerical parameters.<n> Experimental results show that our method outperforms prior approaches in scene complexity, visual quality, and physical accuracy.
  arXiv  Detail & Related papers  (2026-02-16T17:55:25Z)
• PAT3D: Physics-Augmented Text-to-3D Scene Generation [47.18949891825537]
  PAT3D generates 3D objects, infers their spatial relations, and organizes them into a hierarchical scene tree.<n>A differentiable rigid-body simulator ensures realistic object interactions under gravity.<n>Experiments demonstrate that PAT3D substantially outperforms prior approaches in physical plausibility, semantic consistency, and visual quality.
  arXiv  Detail & Related papers  (2025-11-26T23:23:58Z)
• Causal Reasoning Elicits Controllable 3D Scene Generation [35.22855710229319]
  CausalStruct is a novel framework that embeds causal reasoning into 3D scene generation.<n>We construct causal graphs where nodes represent objects and attributes, while edges encode causal dependencies and physical constraints.<n>Our method uses text or images to guide object placement and layout in 3D scenes, with 3D Gaussian Splatting and Score Distillation Sampling improving shape accuracy and rendering stability.
  arXiv  Detail & Related papers  (2025-09-18T01:03:21Z)
• LAYOUTDREAMER: Physics-guided Layout for Text-to-3D Compositional Scene Generation [5.424048651554831]
  We introduce a framework that leverages 3D Gaussian Splatting (3DGS) to facilitate high-quality, physically consistent compositional scene generation guided by text.<n>Specifically, given a text prompt, we convert it into a directed scene graph and adaptively adjust the density and layout of the initial compositional 3D Gaussians.<n>By extracting directed dependencies from the scene graph, we tailor physical and layout energy to ensure both realism and flexibility.
  arXiv  Detail & Related papers  (2025-02-04T02:51:37Z)

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.