VGFlow: Visibility guided Flow Network for Human Reposing

TL;DR

VGFlow introduces a visibility-guided flow network for human reposing that effectively preserves textures, handles occlusions, and adapts to diverse body shapes, achieving state-of-the-art image quality.

Contribution

The paper proposes VGFlow, a novel human reposing method using a visibility-guided flow module and a self-supervised realness loss for improved realism and texture preservation.

Findings

Achieves superior SSIM, LPIPS, and FID scores compared to previous methods.

Effectively handles occlusions and diverse body shapes.

Produces more perceptually realistic reposed images.

Abstract

The task of human reposing involves generating a realistic image of a person standing in an arbitrary conceivable pose. There are multiple difficulties in generating perceptually accurate images, and existing methods suffer from limitations in preserving texture, maintaining pattern coherence, respecting cloth boundaries, handling occlusions, manipulating skin generation, etc. These difficulties are further exacerbated by the fact that the possible space of pose orientation for humans is large and variable, the nature of clothing items is highly non-rigid, and the diversity in body shape differs largely among the population. To alleviate these difficulties and synthesize perceptually accurate images, we propose VGFlow. Our model uses a visibility-guided flow module to disentangle the flow into visible and invisible parts of the target for simultaneous texture preservation and style manipulation. Furthermore, to tackle distinct body shapes and avoid network artifacts, we also incorporate a self-supervised patch-wise "realness" loss to improve the output. VGFlow achieves state-of-the-art results as observed qualitatively and quantitatively on different image quality metrics (SSIM, LPIPS, FID).