Physics-Guided Motion Loss for Video Generation Model

• URL: http://arxiv.org/abs/2506.02244v2
• Date: Thu, 25 Sep 2025 20:44:47 GMT
• Title: Physics-Guided Motion Loss for Video Generation Model
• Authors: Bowen Xue, Giuseppe Claudio Guarnera, Shuang Zhao, Zahra Montazeri,
• Abstract summary: Current video diffusion models generate visually compelling content but often violate basic laws of physics.<n>We introduce a frequency-domain physics prior that improves motion plausibility without modifying model architectures.
• Score: 8.083315267770255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsistent object motion. We introduce a frequency-domain physics prior that improves motion plausibility without modifying model architectures. Our method decomposes common rigid motions (translation, rotation, scaling) into lightweight spectral losses, requiring only 2.7% of frequency coefficients while preserving 97%+ of spectral energy. Applied to Open-Sora, MVDIT, and Hunyuan, our approach improves both motion accuracy and action recognition by ~11% on average on OpenVID-1M (relative), while maintaining visual quality. User studies show 74--83% preference for our physics-enhanced videos. It also reduces warping error by 22--37% (depending on the backbone) and improves temporal consistency scores. These results indicate that simple, global spectral cues are an effective drop-in regularizer for physically plausible motion in video diffusion.

Related papers

• Motion Attribution for Video Generation [97.2515042185441]
  We present Motive, a motion-centric, gradient-based data attribution framework.<n>We use it to study which fine-tuning clips improve or degrade temporal dynamics.<n>To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models.
  arXiv  Detail & Related papers  (2026-01-13T18:59:09Z)
• Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation [76.04880323498598]
  We introduce an algorithm to distill structure-preserving motion priors from an autoregressive video tracking model (SAM2) into a bidirectional video diffusion model (CogVideoX)<n>Experiments on VBench and in human studies show that SAM2VideoX delivers consistent gains.
  arXiv  Detail & Related papers  (2025-12-12T18:56:35Z)
• MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training [46.09617860476419]
  Video diffusion models achieve strong frame-level fidelity but struggle with motion coherence, dynamics and realism.<n>We propose MoGAN, a motion-centric post-training framework that improves motion realism without reward models or human preference data.
  arXiv  Detail & Related papers  (2025-11-26T17:09:03Z)
• Real-Time Motion-Controllable Autoregressive Video Diffusion [79.32730467857535]
  We propose AR-Drag, the first RL-enhanced few-step AR video diffusion model for real-time image-to-video generation with diverse motion control.<n>We first fine-tune a base I2V model to support basic motion control, then further improve it via reinforcement with a trajectory-based reward model.<n>Our design preserves the Markov property through a Self-Rollout learning mechanism and accelerates training by selectively denoising steps.
  arXiv  Detail & Related papers  (2025-10-09T12:17:11Z)
• Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection [73.51855469884195]
  We propose an AI-driven video detection paradigm based on probability flow conservation principles.<n>We develop an NSG-based video detection method (NSG-VD) that computes the Mean Discrepancy (MMD) between NSG features of the test and real videos as a detection metric.
  arXiv  Detail & Related papers  (2025-10-09T11:00:35Z)
• Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation [54.42523027597904]
  We introduce a novel framework that integrates symbolic regression and trajectory-guided image-to-video (I2V) models for physics-grounded video forecasting.<n>Our approach extracts motion trajectories from input videos, uses a retrieval-based pre-training mechanism to enhance symbolic regression, and discovers equations of motion to forecast physically accurate future trajectories.
  arXiv  Detail & Related papers  (2025-07-09T13:28:42Z)
• SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation [56.90807453045657]
  SynMotion is a motion-customized video generation model that jointly leverages semantic guidance and visual adaptation.<n>At the semantic level, we introduce the dual-em semantic comprehension mechanism which disentangles subject and motion representations.<n>At the visual level, we integrate efficient motion adapters into a pre-trained video generation model to enhance motion fidelity and temporal coherence.
  arXiv  Detail & Related papers  (2025-06-30T10:09:32Z)
• MAGIC: Motion-Aware Generative Inference via Confidence-Guided LLM [14.522189177415724]
  MAGIC is a training-free framework for single-image physical property inference and dynamic generation.<n>Our framework generates motion-rich videos from a static image and closes the visual-to-physical gap through a confidence-driven feedback loop.<n> Experiments show that MAGIC outperforms existing physics-aware generative methods in inference accuracy and achieves greater temporal coherence.
  arXiv  Detail & Related papers  (2025-05-22T09:40:34Z)
• RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism [73.38167494118746]
  We propose a framework to improve the realism of motion in generated videos.<n>We advocate for the incorporation of a retrieval mechanism during the generation phase.<n>Our pipeline is designed to apply to any text-to-video diffusion model.
  arXiv  Detail & Related papers  (2025-04-09T08:14:05Z)
• VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models [71.9811050853964]
  VideoJAM is a novel framework that instills an effective motion prior to video generators.<n>VideoJAM achieves state-of-the-art performance in motion coherence.<n>These findings emphasize that appearance and motion can be complementary and, when effectively integrated, enhance both the visual quality and the coherence of video generation.
  arXiv  Detail & Related papers  (2025-02-04T17:07:10Z)
• PhysMotion: Physics-Grounded Dynamics From a Single Image [24.096925413047217]
  We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions.<n>Our approach addresses the limitations of traditional data-driven generative models and result in more consistent physically plausible motions.
  arXiv  Detail & Related papers  (2024-11-26T07:59:11Z)
• Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos [6.093379844890164]
  We propose a novel method to selectively incorporate the physics models with the kinematics observations in an online setting.<n>A recurrent neural network is introduced to realize a Kalman filter that attentively balances the kinematics input and simulated motion.<n>The proposed approach excels in the physics-based human pose estimation task and demonstrates the physical plausibility of the predictive dynamics.
  arXiv  Detail & Related papers  (2024-10-10T10:24:59Z)
• Spectral Motion Alignment for Video Motion Transfer using Diffusion Models [54.32923808964701]
  Spectral Motion Alignment (SMA) is a framework that refines and aligns motion vectors using Fourier and wavelet transforms.<n> SMA learns motion patterns by incorporating frequency-domain regularization, facilitating the learning of whole-frame global motion dynamics.<n>Extensive experiments demonstrate SMA's efficacy in improving motion transfer while maintaining computational efficiency and compatibility across various video customization frameworks.
  arXiv  Detail & Related papers  (2024-03-22T14:47:18Z)
• Diffusion Priors for Dynamic View Synthesis from Monocular Videos [59.42406064983643]
  Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. We first finetune a pretrained RGB-D diffusion model on the video frames using a customization technique. We distill the knowledge from the finetuned model to a 4D representations encompassing both dynamic and static Neural Radiance Fields.
  arXiv  Detail & Related papers  (2024-01-10T23:26:41Z)
• Physics-Guided Human Motion Capture with Pose Probability Modeling [35.159506668475565]
  Existing solutions always adopt kinematic results as reference motions, and the physics is treated as a post-processing module. We employ physics as denoising guidance in the reverse diffusion process to reconstruct human motion from a modeled pose probability distribution. With several iterations, the physics-based tracking and kinematic denoising promote each other to generate a physically plausible human motion.
  arXiv  Detail & Related papers  (2023-08-19T05:28:03Z)
• PhysDiff: Physics-Guided Human Motion Diffusion Model [101.1823574561535]
  Existing motion diffusion models largely disregard the laws of physics in the diffusion process. PhysDiff incorporates physical constraints into the diffusion process. Our approach achieves state-of-the-art motion quality and improves physical plausibility drastically.
  arXiv  Detail & Related papers  (2022-12-05T18:59:52Z)
• Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE [26.13198266911874]
  We propose a novel video generation approach that learns separate distributions for motion and appearance. We employ a two-stage approach where the first stage converts a noise vector to a sequence of keypoints in arbitrary frame rates, and the second stage synthesizes videos based on the given keypoints sequence and the appearance noise vector.
  arXiv  Detail & Related papers  (2021-12-21T03:30:38Z)

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.