SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussians
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914490216349696 |
|---|---|
| author | Li, Mengtian Bai, Yunshu Chu, Yimin Guo, Xinru Liu, Haolin Xie, Zhifeng Chen, Chaofeng |
| author_facet | Li, Mengtian Bai, Yunshu Chu, Yimin Guo, Xinru Liu, Haolin Xie, Zhifeng Chen, Chaofeng |
| contents | We introduce METHODNAME, a novel framework for semantic-aware 3D shape and texture morphing directly from multi-view images. While 3D Gaussian Splatting (3DGS) enables photorealistic rendering, its unstructured nature often leads to catastrophic geometric fragmentation during morphing. Conversely, traditional mesh-based morphing enforces structural integrity but mandates pristine input topology and struggles with complex appearances. Our method resolves this dichotomy by employing a mesh-guided strategy where a coarse, extracted base mesh acts as a flexible geometric anchor. This anchor provides the necessary topological scaffolding to guide unstructured Gaussians, successfully compensating for mesh extraction artifacts and topological limitations. Furthermore, we propose a novel dual-domain optimization strategy that leverages this hybrid representation to establish unsupervised semantic correspondence, synergizing geodesic regularizations for shape preservation with texture-aware constraints for coherent color evolution. This integrated approach ensures stable, physically plausible transformations without requiring labeled data, specialized 3D assets, or category-specific templates. On the proposed TexMorph benchmark, METHODNAME substantially outperforms prior 2D and 3D methods, yielding fully textured, topologically robust 3D morphing while reducing color consistency error (Delta E) by 22.2% and EI by 26.2%. Project page: https://baiyunshu.github.io/GAUSSIANMORPHING.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02034 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussians Li, Mengtian Bai, Yunshu Chu, Yimin Guo, Xinru Liu, Haolin Xie, Zhifeng Chen, Chaofeng Computer Vision and Pattern Recognition We introduce METHODNAME, a novel framework for semantic-aware 3D shape and texture morphing directly from multi-view images. While 3D Gaussian Splatting (3DGS) enables photorealistic rendering, its unstructured nature often leads to catastrophic geometric fragmentation during morphing. Conversely, traditional mesh-based morphing enforces structural integrity but mandates pristine input topology and struggles with complex appearances. Our method resolves this dichotomy by employing a mesh-guided strategy where a coarse, extracted base mesh acts as a flexible geometric anchor. This anchor provides the necessary topological scaffolding to guide unstructured Gaussians, successfully compensating for mesh extraction artifacts and topological limitations. Furthermore, we propose a novel dual-domain optimization strategy that leverages this hybrid representation to establish unsupervised semantic correspondence, synergizing geodesic regularizations for shape preservation with texture-aware constraints for coherent color evolution. This integrated approach ensures stable, physically plausible transformations without requiring labeled data, specialized 3D assets, or category-specific templates. On the proposed TexMorph benchmark, METHODNAME substantially outperforms prior 2D and 3D methods, yielding fully textured, topologically robust 3D morphing while reducing color consistency error (Delta E) by 22.2% and EI by 26.2%. Project page: https://baiyunshu.github.io/GAUSSIANMORPHING.github.io/ |
| title | SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussians |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.02034 |