CVGRApr 14, 2023

One-Shot Stylization for Full-Body Human Images

arXiv:2304.06917v1h-index: 52
Originality Incremental advance
AI Analysis

This work addresses the complex domain of full-body human stylization for applications in digital art and media, representing an incremental advancement over existing face and scene stylization methods.

The paper tackles the problem of full-body human image stylization using a single art character reference, addressing challenges like body shape deformation and pose distribution shifts. The proposed method incorporates a skeleton deformation module and adapts a pose-guided generator, with effectiveness verified through human studies.

The goal of human stylization is to transfer full-body human photos to a style specified by a single art character reference image. Although previous work has succeeded in example-based stylization of faces and generic scenes, full-body human stylization is a more complex domain. This work addresses several unique challenges of stylizing full-body human images. We propose a method for one-shot fine-tuning of a pose-guided human generator to preserve the "content" (garments, face, hair, pose) of the input photo and the "style" of the artistic reference. Since body shape deformation is an essential component of an art character's style, we incorporate a novel skeleton deformation module to reshape the pose of the input person and modify the DiOr pose-guided person generator to be more robust to the rescaled poses falling outside the distribution of the realistic poses that the generator is originally trained on. Several human studies verify the effectiveness of our approach.

Foundations

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

Your Notes