{"ID":5937233,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T04:06:17.856186522Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04653","arxiv_id":"2607.04653","title":"Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising","abstract":"While modern video diffusion models excel in visual fidelity, maintaining long-range physical consistency remains a formidable challenge. Conventional pixel-reconstruction objectives mainly focus on appearance details and often fail to capture the underlying dynamics of a scene. To mitigate this, recent efforts have integrated auxiliary modalities (e.g., optical flow) to introduce physics priors via joint training with video appearance. However, these methods have three main limitations: (1) they do not distinguish the different motion patterns of different entity types; (2) joint modeling of visual and auxiliary modalities can cause capacity conflicts and weaken the pretrained visual prior; and (3) auxiliary modalities may accumulate errors during inference. To address these issues, we propose \\textbf{VPT}, a fine-tuning framework for improving physical consistency in video diffusion models. VPT introduces a role-aware signal that groups entities into agents, controlled objects, passive objects, and background, so that different physical roles can be modeled more clearly. We further propose a modality-decoupled denoising strategy, where the visual and auxiliary channels are assigned independent noise levels. Together with a loss-weight decay strategy, this design makes auxiliary modalities serve as soft constraints rather than strong dependencies, mitigating recursive prediction errors during inference. We also introduce cross-step auto-guidance to further strengthen physical dynamics. Experiments show that VPT improves physical consistency while preserving visual quality, achieving relative gains of 39.4\\% in SA and 17.9\\% in PC on VideoPhy benchmark over Wan2.1-T2V-1.3B, and consistent improvements on VideoPhy-2 benchmark. The project page is available at https://tom-zgt.github.io/VPT.","short_abstract":"While modern video diffusion models excel in visual fidelity, maintaining long-range physical consistency remains a formidable challenge. Conventional pixel-reconstruction objectives mainly focus on appearance details and often fail to capture the underlying dynamics of a scene. To mitigate this, recent efforts have in...","url_abs":"https://arxiv.org/abs/2607.04653","url_pdf":"https://arxiv.org/pdf/2607.04653v1","authors":"[\"Guangting Zheng\",\"Haojing Chen\",\"Hao Li\",\"Jingtao Zhang\",\"Zhen Yang\",\"Xiaosong Jia\",\"Xue Yang\",\"Shaofeng Zhang\",\"Yanyong Zhang\"]","published":"2026-07-06T04:18:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}