TIPS: Text-Induced Pose Synthesis
This addresses the challenge of applying pose transfer in real-world scenarios by using text descriptions instead of target images, though it is incremental as it builds on existing pose transfer methods.
The paper tackles the problem of human pose synthesis and transfer by proposing a text-based approach that divides the task into text-to-pose representation, pose refinement, and pose rendering, generating promising results with significant qualitative and quantitative scores.
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.