ManiFest: Manifold Deformation for Few-shot Image Translation - Archive ouverte HAL Access content directly
Conference Papers Year :

ManiFest: Manifold Deformation for Few-shot Image Translation

(1) , (2) , (1)
1
2

Abstract

Most image-to-image translation methods require a large number of training images, which restricts their applicability. We instead propose ManiFest: a framework for few-shot image translation that learns a context-aware representation of a target domain from a few images only. To enforce feature consistency, our framework learns a style manifold between source and proxy anchor domains (assumed to be composed of large numbers of images). The learned manifold is interpolated and deformed towards the few-shot target domain via patch-based adversarial and feature statistics alignment losses. All of these components are trained simultaneously during a single end-to-end loop. In addition to the general few-shot translation task, our approach can alternatively be conditioned on a single exemplar image to reproduce its specific style. Extensive experiments demonstrate the efficacy of ManiFest on multiple tasks, outperforming the state-of-the-art on all metrics and in both the general- and exemplar-based scenarios. Our code is available at https://github.com/cv-rits/Manifest .

Dates and versions

hal-03498131 , version 1 (20-12-2021)

Identifiers

Cite

Fabio Pizzati, Jean-François Lalonde, Raoul de Charette. ManiFest: Manifold Deformation for Few-shot Image Translation. European Conference on Computer Vision (ECCV), Oct 2022, Tel AViv, Israel. ⟨hal-03498131⟩

Collections

INRIA INRIA2 ANR
21 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More