BiMotion：面向文本引导动态三维角色生成的 B 样条运动
BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
用连续可微的 B 样条曲线替代逐帧离散表示来压缩变长运动序列，这个「固定控制点数的闭式求解器」思路可直接迁移到任何需要变长时序建模的视觉任务（如视频运动生成、动作插值、轨迹表示）。
原文依据 representing motion with continuous differentiable B-spline curves
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本引导的动态三维角色生成已取得快速进展，但生成能够忠实反映丰富文本描述的高质量运动仍然具有挑战性。现有方法由于采用定长时序输入以及离散的逐帧表示，难以捕捉丰富的运动语义，往往只能生成有限的子动作或不连贯的运动。我们通过使用连续可微的 B 样条曲线表示运动来应对这些局限，从而在不改变底层生成模型能力的前提下实现更有效的运动生成。具体而言，我们提出的闭式、拉普拉斯正则化的 B 样条求解器能够高效地将变长运动序列压缩为具有固定数量控制点的紧凑表示。此外，我们引入了用于贴合输入形状的法线融合策略，以及用于提升运动恢复质量的对应关系感知损失与局部刚性损失。为训练模型，我们构建了 BIMO，这是一个包含多样化变长三维运动序列及丰富高质量文本标注的新数据集。大量评估表明，我们的前馈框架 BiMotion 相比现有最优方法能够生成更具表现力、质量更高且与提示更对齐的运动，同时实现更快的生成速度。项目主页为：https://wangmiaowei.github.io/BiMotion.github.io/。
英文原文摘要 1383 字符
Text-guided dynamic 3D character generation has advanced rapidly, yet producing high-quality motion that faithfully reflects rich textual descriptions remains challenging. Existing methods tend to generate limited sub-actions or incoherent motion due to fixed-length temporal inputs and discrete frame-wise representations that fail to capture rich motion semantics. We address these limitations by representing motion with continuous differentiable B-spline curves, enabling more effective motion generation without modifying the capabilities of the underlying generative model. Specifically, our closed-form, Laplacian-regularized B-spline solver efficiently compresses variable-length motion sequences into compact representations with a fixed number of control points. Further, we introduce a normal-fusion strategy for input shape adherence along with correspondence-aware and local-rigidity losses for motion-restoration quality. To train our model, we collate BIMO, a new dataset containing diverse variable-length 3D motion sequences with rich, high-quality text annotations. Extensive evaluations show that our feed-forward framework BiMotion generates more expressive, higher-quality, and better prompt-aligned motions than existing state-of-the-art methods, while also achieving faster generation. Our project page is at: https://wangmiaowei.github.io/BiMotion.github.io/.