We present PoseVocab, a novel pose encoding method that encourages the network to discover the optimal pose embeddings for learning the dynamic human ...

We propose PoseVocab, a novel pose encoding method that encodes dynamic human appearances under various poses for human avatar modeling.

Jul 23, 2023 · We present PoseVocab, a novel pose encoding method that encourages the network to discover the optimal pose embeddings for learning the dynamic human ...

Creating pose-driven human avatars is about modeling the mapping from the low-frequency driving pose to high-frequency dynamic human appearances, ...

Sep 4, 2024 · Overall, PoseVocab effectively encodes the dynamic details of human appearance and enables realistic and generalized animation under novel poses ...

PoseVocab effectively encodes the dynamic details of human appearance and enables realistic and generalized animation under novel poses and outperforms ...

The research into building realistic animatable human avatars has drawn increasing attention in the past few years. Recent developments have demonstrated ...

Duration: 5:18
Posted: Apr 23, 2023

These joint-structured pose embeddings not only encode the dynamic appearances under different key poses, but also factorize the global pose embedding into ...

... Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling" ... PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling".