One-shot Detail Retouching with Patch Space Neural Transformation Blending

TL;DR

This paper presents a novel one-shot learning method for automatic image detail retouching using neural field transformations in patch space, enabling accurate transfer of complex edits from a single example.

Contribution

It introduces a new neural patch space transformation approach for detail retouching that generalizes well from a single example image.

Findings

Accurately transfers complex detail edits from one example.

Effective in both known filter and artist retouching scenarios.

Captures fine details while maintaining generalizability.

Abstract

Photo retouching is a difficult task for novice users as it requires expert knowledge and advanced tools. Photographers often spend a great deal of time generating high-quality retouched photos with intricate details. In this paper, we introduce a one-shot learning based technique to automatically retouch details of an input image based on just a single pair of before and after example images. Our approach provides accurate and generalizable detail edit transfer to new images. We achieve these by proposing a new representation for image to image maps. Specifically, we propose neural field based transformation blending in the patch space for defining patch to patch transformations for each frequency band. This parametrization of the map with anchor transformations and associated weights, and spatio-spectral localized patches, allows us to capture details well while staying generalizable. We evaluate our technique both on known ground truth filters and artist retouching edits. Our method accurately transfers complex detail retouching edits.