Saved in:
Bibliographic Details
Main Authors: Meng, Siwei, Luo, Yawei, Liu, Ping
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.16456
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909806151860224
author Meng, Siwei
Luo, Yawei
Liu, Ping
author_facet Meng, Siwei
Luo, Yawei
Liu, Ping
contents Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequently produce implausible results such as momentum violations and object interpenetrations. Existing physics-aware approaches often rely on task-specific fine-tuning or supervised data, which limits their scalability and applicability. To address the challenge, we present PhyMAGIC, a training-free framework that generates physically consistent motion from a single image. PhyMAGIC integrates a pre-trained image-to-video diffusion model, confidence-guided reasoning via LLMs, and a differentiable physics simulator to produce 3D assets ready for downstream physical simulation without fine-tuning or manual supervision. By iteratively refining motion prompts using LLM-derived confidence scores and leveraging simulation feedback, PhyMAGIC steers generation toward physically consistent dynamics. Comprehensive experiments demonstrate that PhyMAGIC outperforms state-of-the-art video generators and physics-aware baselines, enhancing physical property inference and motion-text alignment while maintaining visual fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16456
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM
Meng, Siwei
Luo, Yawei
Liu, Ping
Computer Vision and Pattern Recognition
Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequently produce implausible results such as momentum violations and object interpenetrations. Existing physics-aware approaches often rely on task-specific fine-tuning or supervised data, which limits their scalability and applicability. To address the challenge, we present PhyMAGIC, a training-free framework that generates physically consistent motion from a single image. PhyMAGIC integrates a pre-trained image-to-video diffusion model, confidence-guided reasoning via LLMs, and a differentiable physics simulator to produce 3D assets ready for downstream physical simulation without fine-tuning or manual supervision. By iteratively refining motion prompts using LLM-derived confidence scores and leveraging simulation feedback, PhyMAGIC steers generation toward physically consistent dynamics. Comprehensive experiments demonstrate that PhyMAGIC outperforms state-of-the-art video generators and physics-aware baselines, enhancing physical property inference and motion-text alignment while maintaining visual fidelity.
title PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.16456