Think Before You Diffuse: LLMs-Guided Physics-Aware Video Generation

• URL: http://arxiv.org/abs/2505.21653v1
• Date: Tue, 27 May 2025 18:26:43 GMT
• Title: Think Before You Diffuse: LLMs-Guided Physics-Aware Video Generation
• Authors: Ke Zhang, Cihan Xiao, Yiqun Mei, Jiacong Xu, Vishal M. Patel,
• Abstract summary: We propose DiffPhy, a generic framework that enables physically-correct and photo-realistic video generation.<n>Our method leverages large language models (LLMs) to explicitly reason a comprehensive physical context from the text prompt.<n>We also establish a high-quality physical video dataset containing diverse phyiscal actions and events to facilitate effective finetuning.
• Score: 28.79821758835663
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent video diffusion models have demonstrated their great capability in generating visually-pleasing results, while synthesizing the correct physical effects in generated videos remains challenging. The complexity of real-world motions, interactions, and dynamics introduce great difficulties when learning physics from data. In this work, we propose DiffPhy, a generic framework that enables physically-correct and photo-realistic video generation by fine-tuning a pre-trained video diffusion model. Our method leverages large language models (LLMs) to explicitly reason a comprehensive physical context from the text prompt and use it to guide the generation. To incorporate physical context into the diffusion model, we leverage a Multimodal large language model (MLLM) as a supervisory signal and introduce a set of novel training objectives that jointly enforce physical correctness and semantic consistency with the input text. We also establish a high-quality physical video dataset containing diverse phyiscal actions and events to facilitate effective finetuning. Extensive experiments on public benchmarks demonstrate that DiffPhy is able to produce state-of-the-art results across diverse physics-related scenarios. Our project page is available at https://bwgzk-keke.github.io/DiffPhy/

Related papers

• Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals [18.86902152614664]
  We investigate using physical forces as a control signal for video generation.<n>We propose force prompts which enable users to interact with images through both localized point forces.<n>We demonstrate that these force prompts can enable videos to respond realistically to physical control signals.
  arXiv  Detail & Related papers  (2025-05-26T01:04:02Z)
• VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior [88.51778468222766]
  Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos.<n>VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics.<n>We propose a novel two-stage image-to-video generation framework that explicitly incorporates physics with vision and language informed physical prior.
  arXiv  Detail & Related papers  (2025-03-30T09:03:09Z)
• VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation [66.58048825989239]
  VideoPhy-2 is an action-centric dataset for evaluating physical commonsense in generated videos.<n>We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos.<n>Our findings reveal major shortcomings, with even the best model achieving only 22% joint performance.
  arXiv  Detail & Related papers  (2025-03-09T22:49:12Z)
• Teaching Video Diffusion Model with Latent Physical Phenomenon Knowledge [49.60640053101214]
  We propose a novel method to teach video diffusion models with latent physical phenomenon knowledge. We generate pseudo-language prompt features based on the aligned spatial relationships between CLIP vision and language encoders. We validate our method extensively through both numerical simulations and real-world observations of physical phenomena.
  arXiv  Detail & Related papers  (2024-11-18T07:26:09Z)
• ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model [9.525806425270428]
  We present emphReinDiffuse that combines reinforcement learning with motion diffusion model to generate physically credible human motions. Our method adapts Motion Diffusion Model to output a parameterized distribution of actions, making them compatible with reinforcement learning paradigms. Our approach outperforms existing state-of-the-art models on two major datasets, HumanML3D and KIT-ML.
  arXiv  Detail & Related papers  (2024-10-09T16:24:11Z)
• PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation [29.831214435147583]
  We present PhysGen, a novel image-to-video generation method. It produces a realistic, physically plausible, and temporally consistent video. Our key insight is to integrate model-based physical simulation with a data-driven video generation process.
  arXiv  Detail & Related papers  (2024-09-27T17:59:57Z)
• VideoPhy: Evaluating Physical Commonsense for Video Generation [93.28748850301949]
  We present VideoPhy, a benchmark designed to assess whether the generated videos follow physical commonsense for real-world activities. We then generate videos conditioned on captions from diverse state-of-the-art text-to-video generative models. Our human evaluation reveals that the existing models severely lack the ability to generate videos adhering to the given text prompts.
  arXiv  Detail & Related papers  (2024-06-05T17:53:55Z)
• Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos [78.49864987061689]
  Traditional methods of impact sound synthesis use physics simulation to obtain a set of physics parameters that could represent and synthesize the sound. Existing video-driven deep learning-based approaches could only capture the weak correspondence between visual content and impact sounds. We propose a physics-driven diffusion model that can synthesize high-fidelity impact sound for a silent video clip.
  arXiv  Detail & Related papers  (2023-03-29T17:59:53Z)
• Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language [92.7638697243969]
  We propose a unified framework that can jointly learn visual concepts and infer physics models of objects from videos and language. This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine.
  arXiv  Detail & Related papers  (2021-10-28T17:59:13Z)

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.