# Image Morphing with Perceptual Constraints and STN Alignment

arXiv: https://arxiv.org/abs/2004.14071 · HTML: https://mlsanity.com/paper/2004.14071/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [StyleAlign: Analysis and Applications of Aligned StyleGAN Models](https://mlsanity.com/paper/2110.11323/) (2021)
- [IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models](https://mlsanity.com/paper/2311.06792/) (2023)
- [FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model](https://mlsanity.com/paper/2507.01953/) (2025)
- [StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation](https://mlsanity.com/paper/2212.10229/) (2022)
- [Versatile Transition Generation with Image-to-Video Diffusion](https://mlsanity.com/paper/2508.01698/) (2025)
- [Textured 3D Regenerative Morphing with 3D Diffusion Prior](https://mlsanity.com/paper/2502.14316/) (2025)
- [Multiview Regenerative Morphing with Dual Flows](https://mlsanity.com/paper/2208.01287/) (2022)
- [Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes](https://mlsanity.com/paper/2102.01161/) (2021)
- [MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing](https://mlsanity.com/paper/2601.00204/) (2026)
- [Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing](https://mlsanity.com/paper/2601.14103/) (2026)
- [Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models](https://mlsanity.com/paper/2511.22425/) (2025)
- [Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition](https://mlsanity.com/paper/2203.09771/) (2022)
- [Video Analysis and Generation via a Semantic Progress Function](https://mlsanity.com/paper/2604.22554/) (2026)

## Abstract (arXiv)

In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set, and maintain a well-paced visual transition from one to the next. In this paper, we propose a conditional GAN morphing framework operating on a pair of input images. The network is trained to synthesize frames corresponding to temporal samples along the transformation, and learns a proper shape prior that enhances the plausibility of intermediate frames. While individual frame plausibility is boosted by the adversarial setup, a special training protocol producing sequences of frames, combined with a perceptual similarity loss, promote smooth transformation over time. Explicit stating of correspondences is replaced with a grid-based freeform deformation spatial transformer that predicts the geometric warp between the inputs, instituting the smooth geometric effect by bringing the shapes into an initial alignment. We provide comparisons to classic as well as latent space morphing techniques, and demonstrate that, given a set of images for self-supervision, our network learns to generate visually pleasing morphing effects featuring believable in-betweens, with robustness to changes in shape and texture, requiring no correspondence annotation.