MorphAny3D：释放结构化隐空间在三维形变中的潜能

MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing

January 1, 2026

作者: Xiaokun Sun, Zeyu Cai, Hao Tang, Ying Tai, Jian Yang, Zhenyu Zhang

cs.AI

摘要

由於難以生成語義一致且時序平滑的變形效果（尤其在跨類別場景下），三維形變技術仍面臨挑戰。本文提出MorphAny3D——一種基於結構化潛在表示（SLAT）的免訓練框架，可實現高質量三維形變。我們的核心發現是：通過在三維生成器的注意力機制中智能融合源目標SLAT特徵，能夠自然產生逼真的形變序列。為此，我們創新性地設計了形變交叉注意力（MCA）模塊以融合源目標結構信息確保連貫性，並提出時序融合自注意力（TFSA）模塊通過引入前一幀特徵來增強時序一致性。此外，定向校正策略有效緩解了形變過程中的姿態模糊問題。大量實驗表明，本方法生成的形變序列達到業界最優水平，即使對於極具挑戰性的跨類別案例亦然。MorphAny3D進一步支持解耦形變與三維風格遷移等高級應用，並可泛化至其他基於SLAT的生成模型。項目頁面：https://xiaokunsun.github.io/MorphAny3D.github.io/

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/.