TIPS: Text-Induced Pose Synthesis

TL;DR

This paper introduces TIPS, a novel text-based human pose transfer method that generates poses from textual descriptions, addressing limitations of existing image-based approaches and including a new dataset for training.

Contribution

The paper proposes a new text-to-pose transfer framework with a three-stage process and introduces the DF-PASS dataset with descriptive pose annotations.

Findings

The method achieves promising qualitative results.

Quantitative scores demonstrate effectiveness.

The approach outperforms existing pose transfer techniques.

Abstract

In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person. Though researchers have recently proposed several methods to achieve this task, most of these techniques derive the target pose directly from the desired target image on a specific dataset, making the underlying process challenging to apply in real-world scenarios as the generation of the target image is the actual aim. In this paper, we first present the shortcomings of current pose transfer algorithms and then propose a novel text-based pose transfer technique to address those issues. We divide the problem into three independent stages: (a) text to pose representation, (b) pose refinement, and (c) pose rendering. To the best of our knowledge, this is one of the first attempts to develop a text-based pose transfer framework where we also introduce a new dataset DF-PASS, by adding descriptive pose annotations for the images of the DeepFashion dataset. The proposed method generates promising results with significant qualitative and quantitative scores in our experiments.