Creating photorealistic materials for 3D rendering requires exceptional artistic skill. Generative models for materials could help, but are currently limited by the lack of high-quality training data. While recent video generative models effortlessly produce realistic material appearances, this knowledge remains entangled with geometry and lighting. We present VideoNeuMat, a two-stage pipeline that extracts reusable neural material assets from video diffusion models. First, we finetune a large video model (Wan 2.1 14B) to generate material sample videos under controlled camera and lighting trajectories, effectively creating a "virtual gonioreflectometer" that preserves the model's material realism while learning a structured measurement pattern. Second, we reconstruct compact neural materials from these videos through a Large Reconstruction Model (LRM) finetuned from a smaller Wan 1.3B video backbone. From 17 generated video frames, our LRM performs single-pass inference to predict neural material parameters that generalize to novel viewing and lighting conditions. The resulting materials exhibit realism and diversity far exceeding the limited synthetic training data, demonstrating that material knowledge can be successfully transferred from internet-scale video models into standalone, reusable neural 3D assets.

翻译：为三维渲染创建逼真的材质需要极高的艺术技巧。材质生成模型虽能提供帮助，但目前受限于高质量训练数据的缺乏。尽管近期的视频生成模型能够轻松生成逼真的材质外观，但这类知识仍与几何和光照信息相互纠缠。本文提出VideoNeuMat——一个从视频扩散模型中提取可复用神经材质资产的两阶段流程。首先，我们微调大型视频模型（Wan 2.1 14B），使其在受控相机与光照轨迹下生成材质样本视频，这相当于构建了一个"虚拟测角反射仪"，既能保持模型的材质真实感，又能学习结构化测量模式。其次，我们通过基于较小规模Wan 1.3B视频主干微调的大型重建模型（LRM），从这些视频中重建紧凑的神经材质。仅需17帧生成视频，我们的LRM即可通过单次推理预测神经材质参数，并能泛化至新的视角与光照条件。所得材质展现出的真实性与多样性远超有限的合成训练数据，证明材质知识能够成功从互联网规模的视频模型迁移至独立、可复用的神经三维资产中。