Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting
This enables more flexible animation and motion transfer across subjects without relying on traditional models, though it is incremental in improving neural implicit methods.
The paper tackles the problem of motion retargeting and animation by disentangling subject-specific and pose-specific details using a neural implicit pose network, achieving state-of-the-art results on benchmarks.
We present HIPNet, a neural implicit pose network trained on multiple subjects across many poses. HIPNet can disentangle subject-specific details from pose-specific details, effectively enabling us to retarget motion from one subject to another or to animate between keyframes through latent space interpolation. To this end, we employ a hierarchical skeleton-based representation to learn a signed distance function on a canonical unposed space. This joint-based decomposition enables us to represent subtle details that are local to the space around the body joint. Unlike previous neural implicit method that requires ground-truth SDF for training, our model we only need a posed skeleton and the point cloud for training, and we have no dependency on a traditional parametric model or traditional skinning approaches. We achieve state-of-the-art results on various single-subject and multi-subject benchmarks.