CVLGIVJan 5, 2020

A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis

arXiv:2001.01259v12 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of pose-guided person image synthesis for computer vision applications, offering a simpler and more efficient solution compared to existing complex models.

The paper tackles the problem of generating photorealistic images of humans in arbitrary poses by proposing a pose transformation GAN using Residual Learning without additional features, achieving robustness to illumination, occlusion, distortion, and scale, and demonstrating superiority over existing methods on two large datasets with qualitative and quantitative results.

Generating photorealistic images of human subjects in any unseen pose have crucial applications in generating a complete appearance model of the subject. However, from a computer vision perspective, this task becomes significantly challenging due to the inability of modelling the data distribution conditioned on pose. Existing works use a complicated pose transformation model with various additional features such as foreground segmentation, human body parsing etc. to achieve robustness that leads to computational overhead. In this work, we propose a simple yet effective pose transformation GAN by utilizing the Residual Learning method without any additional feature learning to generate a given human image in any arbitrary pose. Using effective data augmentation techniques and cleverly tuning the model, we achieve robustness in terms of illumination, occlusion, distortion and scale. We present a detailed study, both qualitative and quantitative, to demonstrate the superiority of our model over the existing methods on two large datasets.

Foundations

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

Your Notes