Structure-Aware Human Body Reshaping with Adaptive Affinity-Graph Network

2024-04-22

arXiv.org

AI Summary

Existing automatic human body reshaping methods often neglect global inter-part coordination, resulting in unnatural deformations and poor visual consistency. To address this, we propose a flow-guided portrait editing framework for holistic, coordinated body reshaping. First, we design an Adaptive All-pairwise Affinity Graph (AAG) module to explicitly model global spatial affinity relationships across anatomical regions. Second, we introduce a Body Shape Discriminator (BSD) that jointly incorporates SRM-based high-frequency filtering and spatial-semantic guidance, overcoming limitations of local deformation modeling and pixel-level fidelity optimization. Evaluated on the BR-5K benchmark, our method achieves state-of-the-art performance across all quantitative metrics—including LPIPS, FID, and SSIM—as well as comprehensive human perceptual assessments. It significantly enhances the naturalness, structural consistency, and aesthetic quality of body shape adjustments.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Intelligent Robots: Manipulation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Given a source portrait, the automatic human body reshaping task aims at editing it to an aesthetic body shape. As the technology has been widely used in media, several methods have been proposed mainly focusing on generating optical flow to warp the body shape. However, those previous works only consider the local transformation of different body parts (arms, torso, and legs), ignoring the global affinity, and limiting the capacity to ensure consistency and quality across the entire body. In this paper, we propose a novel Adaptive Affinity-Graph Network (AAGN), which extracts the global affinity between different body parts to enhance the quality of the generated optical flow. Specifically, our AAGN primarily introduces the following designs: (1) we propose an Adaptive Affinity-Graph (AAG) Block that leverages the characteristic of a fully connected graph. AAG represents different body parts as nodes in an adaptive fully connected graph and captures all the affinities between nodes to obtain a global affinity map. The design could better improve the consistency between body parts. (2) Besides, for high-frequency details are crucial for photo aesthetics, a Body Shape Discriminator (BSD) is designed to extract information from both high-frequency and spatial domain. Particularly, an SRM filter is utilized to extract high-frequency details, which are combined with spatial features as input to the BSD. With this design, BSD guides the Flow Generator (FG) to pay attention to various fine details rather than rigid pixel-level fitting. Extensive experiments conducted on the BR-5K dataset demonstrate that our framework significantly enhances the aesthetic appeal of reshaped photos, surpassing all previous work to achieve state-of-the-art in all evaluation metrics.

Problem

• Automatic Body Modification
• Proportional Coordination
• Aesthetic Quality

Innovation

• Adaptive Affinity Graph Network
• Body Shape Discriminator
• Natural Pose Modification