CVDec 22, 2023

StyleRetoucher: Generalized Portrait Image Retouching with GAN Priors

arXiv:2312.14389v13 citationsh-index: 8IEEE Trans Vis Comput Graph
Originality Incremental advance
AI Analysis

This addresses the tedious and time-consuming task of portrait retouching for professionals and users, though it is incremental as it builds on existing GAN-based methods.

The paper tackles the problem of automatic portrait image retouching by introducing StyleRetoucher, a framework that uses StyleGAN priors to improve skin condition while preserving facial details, achieving superior generalization and performance over existing methods as validated by quantitative and user studies.

Creating fine-retouched portrait images is tedious and time-consuming even for professional artists. There exist automatic retouching methods, but they either suffer from over-smoothing artifacts or lack generalization ability. To address such issues, we present StyleRetoucher, a novel automatic portrait image retouching framework, leveraging StyleGAN's generation and generalization ability to improve an input portrait image's skin condition while preserving its facial details. Harnessing the priors of pretrained StyleGAN, our method shows superior robustness: a). performing stably with fewer training samples and b). generalizing well on the out-domain data. Moreover, by blending the spatial features of the input image and intermediate features of the StyleGAN layers, our method preserves the input characteristics to the largest extent. We further propose a novel blemish-aware feature selection mechanism to effectively identify and remove the skin blemishes, improving the image skin condition. Qualitative and quantitative evaluations validate the great generalization capability of our method. Further experiments show StyleRetoucher's superior performance to the alternative solutions in the image retouching task. We also conduct a user perceptive study to confirm the superior retouching performance of our method over the existing state-of-the-art alternatives.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes