Language2Pose: Natural Language Grounded Pose Forecasting
This addresses the multimodal challenge of mapping language to motion for applications like animation and robotics, but it is incremental as it builds on existing data-driven approaches.
The paper tackles the problem of generating 3D pose animations from natural language descriptions, such as for movie scripts or virtual humans, by introducing a neural architecture that learns a joint embedding of language and pose. The result is that the approach generates more accurate animations and is deemed more visually representative by humans compared to other data-driven methods.
Generating animations from natural language sentences finds its applications in a a number of domains such as movie script visualization, virtual human animation and, robot motion planning. These sentences can describe different kinds of actions, speeds and direction of these actions, and possibly a target destination. The core modeling challenge in this language-to-pose application is how to map linguistic concepts to motion animations. In this paper, we address this multimodal problem by introducing a neural architecture called Joint Language to Pose (or JL2P), which learns a joint embedding of language and pose. This joint embedding space is learned end-to-end using a curriculum learning approach which emphasizes shorter and easier sequences first before moving to longer and harder ones. We evaluate our proposed model on a publicly available corpus of 3D pose data and human-annotated sentences. Both objective metrics and human judgment evaluation confirm that our proposed approach is able to generate more accurate animations and are deemed visually more representative by humans than other data driven approaches.