Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs
By: Sinan Mutlu , Georgios F. Angelis , Savas Ozkan and more
Potential Business Impact:
Makes virtual bodies move like real ones.
Realistic and smooth full-body tracking is crucial for immersive AR/VR applications. Existing systems primarily track head and hands via Head Mounted Devices (HMDs) and controllers, making the 3D full-body reconstruction in-complete. One potential approach is to generate the full-body motions from sparse inputs collected from limited sensors using a Neural Network (NN) model. In this paper, we propose a novel method based on a multi-layer perceptron (MLP) backbone that is enhanced with residual connections and a novel NN-component called Memory-Block. In particular, Memory-Block represents missing sensor data with trainable code-vectors, which are combined with the sparse signals from previous time instances to improve the temporal consistency. Furthermore, we formulate our solution as a multi-task learning problem, allowing our MLP-backbone to learn robust representations that boost accuracy. Our experiments show that our method outperforms state-of-the-art baselines by substantially reducing prediction errors. Moreover, it achieves 72 FPS on mobile HMDs that ultimately improves the accuracy-running time tradeoff.
Similar Papers
Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows
CV and Pattern Recognition
Makes virtual bodies move more realistically and faster.
Towards Arbitrary Motion Completing via Hierarchical Continuous Representation
CV and Pattern Recognition
Makes videos of people move smoother, faster, or slower.
A Personalized Data-Driven Generative Model of Human Motion
Graphics
Makes robots move like real people.