Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models
This addresses the need for automated, high-quality 3D morphing in computer graphics and AI, reducing reliance on manual preprocessing and improving generalization.
The paper tackles the problem of high-fidelity textured 3D morphing by introducing WUKONG, a training-free framework that uses flow-based transformers to generate smooth 3D transitions from source and target prompts, achieving superior results compared to state-of-the-art methods.
We present WUKONG, a novel training-free framework for high-fidelity textured 3D morphing that takes a pair of source and target prompts (image or text) as input. Unlike conventional methods -- which rely on manual correspondence matching and deformation trajectory estimation (limiting generalization and requiring costly preprocessing) -- WUKONG leverages the generative prior of flow-based transformers to produce high-fidelity 3D transitions with rich texture details. To ensure smooth shape transitions, we exploit the inherent continuity of flow-based generative processes and formulate morphing as an optimal transport barycenter problem. We further introduce a sequential initialization strategy to prevent abrupt geometric distortions and preserve identity coherence. For faithful texture preservation, we propose a similarity-guided semantic consistency mechanism that selectively retains high-frequency details and enables precise control over blending dynamics. This empowers WUKONG to support both global texture transitions and identity-preserving texture morphing, catering to diverse generation needs. Extensive quantitative and qualitative evaluations demonstrate that WUKONG significantly outperforms state-of-the-art methods, achieving superior results across diverse geometry and texture variations.