PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

• URL: http://arxiv.org/abs/2605.05163v1
• Date: Wed, 06 May 2026 17:33:23 GMT
• Title: PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
• Abstract summary: We introduce PhysForge, a framework for synthesizing physics-grounded 3D assets.<n>A "physical architect" acts as a "physical architect" to plan a "Hierarchical Physical Blueprint"<n>A physics-grounded diffusion model realizes this blueprint by high-fidelity geometry alongside precise kinematic parameters.
• Score: 39.46909309051163
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in functional logic and hierarchical physics. To bridge this gap, we introduce PhysForge, a decoupled two-stage framework supported by PhysDB, a large-scale dataset of 150,000 assets with four-tier physical annotations. First, a VLM acts as a "physical architect" to plan a "Hierarchical Physical Blueprint" defining material, functional, and kinematic constraints. Second, a physics-grounded diffusion model realizes this blueprint by synthesizing high-fidelity geometry alongside precise kinematic parameters via a novel KineVoxel Injection (KVI) mechanism. Experiments demonstrate that PhysForge produces functionally plausible, simulation-ready assets, providing a robust data engine for interactive 3D content and embodied agents.

Related papers

• Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition [10.183626550724352]
  Gen2Physics grounds generated meshes in physics by automatically decomposing them into constituent material components.<n>Our pipeline integrates a fine-tuned Vision Transformer for dense material segmentation, a robust 2D-to-3D consistency projection, and a Vision-Language Model (VLM) guided refinement.
  arXiv  Detail & Related papers  (2026-08-24T22:18:44Z)
• Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection [0.14323566945483496]
  We present a self-dimensional framework for learning implicit 3D physical dynamics directly from video-derived supervisory signals.<n>We address this by shifting the predictive bottleneck from 2D image space to a lifted' 3D Volumetric Latent Space.<n>Unlike state-of-the-art hybrid models that rely on explicit classical simulators for training and/or inference, our architecture tracks material states implicitly within high-supervised V-JEPA features.
  arXiv  Detail & Related papers  (2026-06-24T22:06:35Z)
• PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects [60.069451811298315]
  We introduce PhysX- Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types.<n>Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression.<n>In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories.
  arXiv  Detail & Related papers  (2026-05-20T17:59:01Z)
• PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment [23.066204478030627]
  Video Models (VDMs) offer a promising approach for simulating dynamic scenes and environments.<n>Existing models often generate temporally incoherent content that violates basic physical intuition.<n>We propose PhysAlign, an efficient framework for physics-coherent image-to-videoI (2V) generation.
  arXiv  Detail & Related papers  (2026-03-14T05:44:18Z)
• PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image [67.76547268461411]
  PhysX-Anything is the first simulation-ready physical 3D generative framework.<n>It produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes.<n>It reduces the number of tokens by 193x, enabling explicit geometry learning within standard VLM token budgets.
  arXiv  Detail & Related papers  (2025-11-17T17:59:53Z)
• PhysX-3D: Physical-Grounded 3D Asset Generation [48.78065667043986]
  Existing 3D generation primarily emphasizes geometries and textures while neglecting physical-grounded modeling.<n>We present PhysXNet - the first physics-grounded 3D dataset systematically annotated across five foundational dimensions.<n>We also propose textbfPhysXGen, a feed-forward framework for physics-grounded image-to-3D asset generation.
  arXiv  Detail & Related papers  (2025-07-16T17:59:35Z)
• PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View Synthesis [62.283499219361595]
  PhysGaia is a physics-aware dataset specifically designed for Dynamic Novel View Synthesis (DyNVS)<n>Our dataset provides complex dynamic scenarios with rich interactions among multiple objects.<n>PhysGaia will significantly advance research in dynamic view synthesis, physics-based scene understanding, and deep learning models integrated with physical simulation.
  arXiv  Detail & Related papers  (2025-06-03T12:19:18Z)
• PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation [62.53760963292465]
  PhysDreamer is a physics-based approach that endows static 3D objects with interactive dynamics. We present our approach on diverse examples of elastic objects and evaluate the realism of the synthesized interactions through a user study.
  arXiv  Detail & Related papers  (2024-04-19T17:41:05Z)

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.