AniMatrix：一个以艺术而非物理思考的动画视频生成模型
AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics
AI总结：
AniMatrix通过双通道条件机制和三步过渡，以艺术正确性替代物理正确性，实现动画视频生成，其在五个动画生产维度上获得专业动画师的认可。
摘要：
视频生成模型通常将物理真实性作为先验知识。动画故意违反物理定律：模糊、冲击帧、Chibi变化等；其成千上万的共存艺术风格没有单一的“动画物理”可以被模型吸收。基于物理的模型因此会扁平化定义该媒介的艺术性或在风格多样性下崩溃。我们提出了AniMatrix，一个以艺术而非物理正确性为目标的视频生成模型，通过双通道条件机制和三步过渡：重新定义正确性、覆盖物理先验、区分艺术与失败。首先，一个生产知识系统将动画编码为可控制的生产变量（风格、运动、摄像、VFX）的结构化分类法，AniCaption从像素中推断这些变量作为导演指令。可训练的标签编码器保留了该分类法的字段-值结构，而冻结的T5编码器处理自由形式的叙述；双路径注入（交叉注意力用于细粒度控制，AdaLN调制用于全局强制）确保类别指令不会被开放式文本稀释。其次，一种风格-运动-变形课程将模型从近物理运动过渡到完整的动画表现力。第三，变形感知偏好优化与领域特定奖励模型将有意的艺术性与病理崩溃分开。在针对动画特定的人类评估中，五个生产维度由专业动画师评分，AniMatrix在五个维度中四个排名第一，其在提示理解（+0.70，+22.4%）和艺术运动（+0.55，+16.9%）方面相对于Seedance-Pro 1.0的提升最大。我们正在准备配套资源以公开发布，以支持可重复性和后续研究。
英文摘要：
Video generation models internalize physical realism as their prior. Anime deliberately violates physics: smears, impact frames, chibi shifts; and its thousands of coexisting artistic conventions yield no single "physics of anime" a model can absorb. Physics-biased models therefore flatten the artistry that defines the medium or collapse under its stylistic variance. We present AniMatrix, a video generation model that targets artistic rather than physical correctness through a dual-channel conditioning mechanism and a three-step transition: redefine correctness, override the physics prior, and distinguish art from failure. First, a Production Knowledge System encodes anime as a structured taxonomy of controllable production variables (Style, Motion, Camera, VFX), and AniCaption infers these variables from pixels as directorial directives. A trainable tag encoder preserves the field-value structure of this taxonomy while a frozen T5 encoder handles free-form narrative; dual-path injection (cross-attention for fine-grained control, AdaLN modulation for global enforcement) ensures categorical directives are never diluted by open-ended text. Second, a style-motion-deformation curriculum transitions the model from near-physical motion to full anime expressiveness. Third, deformation-aware preference optimization with a domain-specific reward model separates intentional artistry from pathological collapse. On an anime-specific human evaluation with five production dimensions scored by professional animators, AniMatrix ranks first on four of five, with the largest gains over Seedance-Pro 1.0 on Prompt Understanding (+0.70, +22.4 percent) and Artistic Motion (+0.55, +16.9 percent). We are preparing accompanying resources for public release to support reproducibility and follow-up research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
