One-shot Detail Retouching with Patch Space Neural Transformation Blending
This addresses the difficulty for novice users in performing expert-level photo retouching, though it is an incremental improvement in image editing methods.
The paper tackles the problem of automating photo detail retouching for novice users by introducing a one-shot learning technique that transfers edits from a single before-after image pair to new images, achieving accurate and generalizable results as evaluated on ground truth filters and artist edits.
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.