FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908586385342464 |
|---|---|
| author | Bizzi, Arthur Grynberg, Matias Matias, Vitor Perazzo, Daniel Lima, João Paulo Velho, Luiz Gonçalves, Nuno Pereira, João Schardong, Guilherme Novello, Tiago |
| author_facet | Bizzi, Arthur Grynberg, Matias Matias, Vitor Perazzo, Daniel Lima, João Paulo Velho, Luiz Gonçalves, Nuno Pereira, João Schardong, Guilherme Novello, Tiago |
| contents | Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit neural representations (INRs) for modeling such deformations, due to their meshlessness and differentiability; however, extracting coherent and accurate morphings from standard MLPs typically relies on costly regularizations, which often lead to unstable training and prevent effective feature alignment. To overcome these limitations, we propose FLOWING (FLOW morphING), a framework that recasts warping as the construction of a differential vector flow, naturally ensuring continuity, invertibility, and temporal coherence by encoding structural flow properties directly into the network architectures. This flow-centric approach yields principled and stable transformations, enabling accurate and structure-preserving morphing of both 2D images and 3D shapes. Extensive experiments across a range of applications - including face and image morphing, as well as Gaussian Splatting morphing - show that FLOWING achieves state-of-the-art morphing quality with faster convergence. Code and pretrained models are available at http://schardong.github.io/flowing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09537 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLOWING: Implicit Neural Flows for Structure-Preserving Morphing Bizzi, Arthur Grynberg, Matias Matias, Vitor Perazzo, Daniel Lima, João Paulo Velho, Luiz Gonçalves, Nuno Pereira, João Schardong, Guilherme Novello, Tiago Computer Vision and Pattern Recognition I.4.0 Morphing is a long-standing problem in vision and computer graphics, requiring a time-dependent warping for feature alignment and a blending for smooth interpolation. Recently, multilayer perceptrons (MLPs) have been explored as implicit neural representations (INRs) for modeling such deformations, due to their meshlessness and differentiability; however, extracting coherent and accurate morphings from standard MLPs typically relies on costly regularizations, which often lead to unstable training and prevent effective feature alignment. To overcome these limitations, we propose FLOWING (FLOW morphING), a framework that recasts warping as the construction of a differential vector flow, naturally ensuring continuity, invertibility, and temporal coherence by encoding structural flow properties directly into the network architectures. This flow-centric approach yields principled and stable transformations, enabling accurate and structure-preserving morphing of both 2D images and 3D shapes. Extensive experiments across a range of applications - including face and image morphing, as well as Gaussian Splatting morphing - show that FLOWING achieves state-of-the-art morphing quality with faster convergence. Code and pretrained models are available at http://schardong.github.io/flowing. |
| title | FLOWING: Implicit Neural Flows for Structure-Preserving Morphing |
| topic | Computer Vision and Pattern Recognition I.4.0 |
| url | https://arxiv.org/abs/2510.09537 |