GaussianMorphing: Mesh-Guided 3D Gaussians for Semantic-Aware Object Morphing
This addresses the challenge of high-fidelity 3D object morphing for applications like animation or visualization, though it appears incremental as it builds on existing 3D Gaussian Splatting methods.
The paper tackles the problem of semantic-aware 3D shape and texture morphing from multi-view images, achieving a 22.2% reduction in color consistency error and a 26.2% reduction in EI on a new benchmark.
We introduce GaussianMorphing, a novel framework for semantic-aware 3D shape and texture morphing from multi-view images. Previous approaches usually rely on point clouds or require pre-defined homeomorphic mappings for untextured data. Our method overcomes these limitations by leveraging mesh-guided 3D Gaussian Splatting (3DGS) for high-fidelity geometry and appearance modeling. The core of our framework is a unified deformation strategy that anchors 3DGaussians to reconstructed mesh patches, ensuring geometrically consistent transformations while preserving texture fidelity through topology-aware constraints. In parallel, our framework establishes unsupervised semantic correspondence by using the mesh topology as a geometric prior and maintains structural integrity via physically plausible point trajectories. This integrated approach preserves both local detail and global semantic coherence throughout the morphing process with out requiring labeled data. On our proposed TexMorph benchmark, GaussianMorphing substantially outperforms prior 2D/3D methods, reducing color consistency error ($ΔE$) by 22.2% and EI by 26.2%. Project page: https://baiyunshu.github.io/GAUSSIANMORPHING.github.io/