Publication
Text-Based Motion Synthesis with a Hierarchical Two-Stream RNN
Anindita Ghosh; Noshaba Cheema; Cennet Oguz; Christian Theobalt; Philipp Slusallek
In: SIGGRAPH '21 Posters. ACM Siggraph (Siggraph-21), August 9-13, Virtual, ACM, 2021.
Abstract
We present a learning-based method for generating animated 3D pose sequences depicting multiple sequential or superimposed actions provided in long, compositional sentences. We propose a hierarchical two-stream sequential model to explore a finer joint-level mapping between natural language sentences and the corresponding 3D pose sequences of the motions. We learn two manifold representations of the motion — one each for the upper body and the lower body movements. We evaluate our proposed model on the publicly available KIT Motion-Language Dataset containing 3D pose data with human-annotated sentences. Experimental results show that our model advances the state-of-the-art on text-based motion synthesis in objective evaluations by a margin of 50%.
Projects
- IMPRESS - Improving Embeddings with Semantic Knowledge
- XAINES - Explaining AI with Narratives
- Carousel+ - Embodied Online Dancing with Digital Characters