Pose Guided Person Image Generation with Hidden p-Norm Regression

TL;DR

This paper introduces a novel pose-guided person image generation method that models the pose-appearance relation as a p-norm regression in hidden space, enabling end-to-end training and adaptability to supervised or unsupervised scenarios.

Contribution

It proposes a new hidden space p-norm regression approach for pose-guided image generation, supporting both supervised and unsupervised training and multi-shot generation.

Findings

Achieves competitive results on Market-1501 dataset

Supports both supervised and unsupervised training modes

Enables multi-shot person image generation

Abstract

In this paper, we propose a novel approach to solve the pose guided person image generation task. We assume that the relation between pose and appearance information can be described by a simple matrix operation in hidden space. Based on this assumption, our method estimates a pose-invariant feature matrix for each identity, and uses it to predict the target appearance conditioned on the target pose. The estimation process is formulated as a p-norm regression problem in hidden space. By utilizing the differentiation of the solution of this regression problem, the parameters of the whole framework can be trained in an end-to-end manner. While most previous works are only applicable to the supervised training and single-shot generation scenario, our method can be easily adapted to unsupervised training and multi-shot generation. Extensive experiments on the challenging Market-1501 dataset show that our method yields competitive performance in all the aforementioned variant scenarios.