IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models

arXiv:2311.06792v2 Announce Type: replace
Abstract: We present a diffusion-based image morphing approach with perceptually-uniform sampling (IMPUS) that produces smooth, direct and realistic interpolations given an image pair. The embeddings of two images may lie on distinct conditioned distributions of a latent diffusion model, especially when they have significant semantic difference. To bridge this gap, we interpolate in the locally linear and continuous text embedding space and Gaussian latent space. We first optimize the endpoint text embeddings and then map the …

abstract arxiv cs.cv difference diffusion diffusion model diffusion models embeddings image images sampling semantic type uniform