FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
This addresses the challenge of stable and accurate morphing for applications like face and image morphing, though it appears incremental by building on existing implicit neural representations.
The paper tackled the problem of morphing in vision and computer graphics by proposing FLOWING, a framework that uses implicit neural flows to ensure continuity, invertibility, and temporal coherence, achieving state-of-the-art morphing quality with faster convergence across 2D images and 3D shapes.
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.