无需训练，用结构化潜空间实现高质量3D形态变化。
MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing
- 在3D生成器注意力机制中融合源与目标特征，生成连贯变形。
- 跨类别形态变化效果领先，序列时间一致性显著提升。
- 适合需要快速生成3D形态动画的开发者和设计师。
3D形态变化因语义一致性和时间平滑性难以保证而仍具挑战，尤其在跨类别场景下。我们提出MorphAny3D，一种无需训练的框架，利用结构化潜空间（SLAT）表示实现高质量3D形态变化。核心思想是将源与目标SLAT特征智能地融入3D生成器的注意力机制中，自然生成合理形态序列。为此，我们引入形态交叉注意力（MCA）以保证结构一致性，并设计时序融合自注意力（TFSA），通过融合前帧特征增强时间连续性。此外，姿态校正策略有效缓解了形态步骤中的姿态模糊问题。大量实验表明，该方法在跨类别情形下仍能生成最先进的形态序列。MorphAny3D还支持解耦形态变化与3D风格迁移等高级应用，可泛化至其他基于SLAT的生成模型。
原文摘要 · Abstract (English)
3D morphing remains challenging due to the difficulty of generating semantically consistent and temporally smooth deformations, especially across categories. We present MorphAny3D, a training-free framework that leverages Structured Latent (SLAT) representations for high-quality 3D morphing. Our key insight is that intelligently blending source and target SLAT features within the attention mechanisms of 3D generators naturally produces plausible morphing sequences. To this end, we introduce Morphing Cross-Attention (MCA), which fuses source and target information for structural coherence, and Temporal-Fused Self-Attention (TFSA), which enhances temporal consistency by incorporating features from preceding frames. An orientation correction strategy further mitigates the pose ambiguity within the morphing steps. Extensive experiments show that our method generates state-of-the-art morphing sequences, even for challenging cross-category cases. MorphAny3D further supports advanced applications such as decoupled morphing and 3D style transfer, and can be generalized to other SLAT-based generative models. Project page: https://xiaokunsun.github.io/MorphAny3D.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。