Pose Guided Person Image Generation with Hidden p-Norm Regression
This work addresses the problem of generating realistic person images from poses for applications like virtual try-on or surveillance, offering a flexible method that extends to unsupervised and multi-shot settings, though it is incremental in building on existing pose-guided generation approaches.
The paper tackles pose guided person image generation by modeling pose-appearance relations as a matrix operation in hidden space, using p-norm regression to estimate pose-invariant features, and achieves competitive performance on the Market-1501 dataset in supervised, unsupervised, and multi-shot scenarios.
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.