Bikesh Regmi

TextPose: Language-Conditioned Static 3D Human Pose Synthesis via Discrete Pose Tokens

This paper addresses static text-to-pose synthesis. Given a natural language description of a body configuration, the task is to generate the corresponding single-frame 3D human pose as a set of J root-relative joint positions in ℝJ×3. Discrete latent representations have been applied successfully to text-to-motion gen...