Structure-Aware Flow Generation for Human Body Reshaping

TL;DR

This paper introduces a novel end-to-end flow generation method guided by body structural priors for human body reshaping, achieving high controllability and visual quality in portrait photo retouching.

Contribution

It proposes a structure-aware flow generation architecture with a compositional attention mechanism and introduces the large-scale BR-5K dataset for comprehensive evaluation.

Findings

Outperforms state-of-the-art methods in visual quality and controllability.

Demonstrates efficiency and robustness across diverse poses and garments.

Provides the first large-scale dataset for body reshaping evaluation.

Abstract

Body reshaping is an important procedure in portrait photo retouching. Due to the complicated structure and multifarious appearance of human bodies, existing methods either fall back on the 3D domain via body morphable model or resort to keypoint-based image deformation, leading to inefficiency and unsatisfied visual quality. In this paper, we address these limitations by formulating an end-to-end flow generation architecture under the guidance of body structural priors, including skeletons and Part Affinity Fields, and achieve unprecedentedly controllable performance under arbitrary poses and garments. A compositional attention mechanism is introduced for capturing both visual perceptual correlations and structural associations of the human body to reinforce the manipulation consistency among related parts. For a comprehensive evaluation, we construct the first large-scale body reshaping dataset, namely BR-5K, which contains 5,000 portrait photos as well as professionally retouched targets. Extensive experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods in terms of visual performance, controllability, and efficiency. The dataset is available at our website: https://github.com/JianqiangRen/FlowBasedBodyReshaping.