BiMotion: B-spline 动作 for 文本引导的动态 3D 人物生成
BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
AI总结：
BiMotion 通过 B-spline 曲线生成高质量文本引导的动态 3D 人物动作，提升动作生成的表现力和质量。
摘要：
文本引导的动态 3D 人物生成已迅速发展，但生成高质量的动作以忠实反映丰富的文本描述仍具挑战性。现有方法由于固定长度的时间输入和离散帧表示，倾向于生成有限的子动作或不连贯的动作，无法捕捉丰富的动作语义。我们通过用连续可微的 B-spline 曲线表示动作，解决这些限制，从而更有效地生成动作，而不修改底层生成模型的能力。具体而言，我们的闭式解、拉普拉斯正则化的 B-spline 解算器能够将可变长度的动作序列压缩成紧凑的表示，使用固定数量的控制点。进一步，我们引入了用于输入形状适应的法线融合策略，以及对应关系感知和局部刚性损失以提高动作恢复质量。为了训练我们的模型，我们收集了 BIMO，一个包含多样可变长度 3D 动作序列和丰富高质量文本注释的新数据集。广泛的评估显示，我们的 feed-forward 框架 BiMotion 生成的动作比现有最先进方法更具表现力、更高质量和更好的提示对齐，同时也能实现更快的生成。我们的项目页面位于：https://wangmiaowei.github.io/BiMotion.github.io/。
英文摘要：
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/.
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。
