Name
Title | ||
|---|---|---|
Human Motion Generation By Stochastic Conditioning Of Deep Recurrent Networks On Pose Manifolds |
Abstract | ||
|---|---|---|
Human motion generation is a stochastic process. The 3D motion generation task requires efficient regulation of stochasticity and a controlled approach for error-accumulation. Current generation approaches either fail to check error-amplitude or to preserve the signal. In this paper, we present a stochastic approach for 3D human motion generation. To this end, we design a fully differentiable, end-to-end, block-based autoregressive recurrent neural network (RNN) architecture. The proposed model incorporates variable auto-conditioning length along with probabilistic variational inference on the RNN hidden-state, to regulate stochasticity. We separately train an auto-encoder to bound skeletons on a known manifold of valid-poses. We extensively test the proposed approach on publicly available Motion-Capture benchmarks. The quantitative and qualitative evaluations indicate the superiority of the proposed approach in comparison to state-of-the-art on long-term motion generation while achieving comparable performance on short-term prediction task. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICIP40778.2020.9190765 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Motion generation, pose-manifold, sequence learning, residual connections | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Himanshu Buckchash | 1 | 0 | 0.34 |
| Balasubramanian Raman | 2 | 679 | 70.23 |