残差ベクトル量子化によるポーズ表現の表現力と分離性の向上
Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization
ポーズコードに残差ベクトル量子化で連続的な動きの特徴を加え、テキストからの人間動作生成の表現力と制御性を高めた研究。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sukhyun Jeong, Hong-Gi Shin, Yong-Hoon Choi
分類: cs.CV, cs.RO
原文アブストラクト
Recent progress in text-to-motion has advanced both 3D human motion generation and text-based motion control. Controllable motion generation (CoMo), which enables intuitive control, typically relies on pose code representations, but discrete pose codes alone cannot capture fine-grained motion details, limiting expressiveness. To overcome this, we propose a method that augments pose code-based latent representations with continuous motion features using residual vector quantization (RVQ). This design preserves the interpretability and manipulability of pose codes while effectively capturing subtle motion characteristics such as high-frequency details. Experiments on the HumanML3D dataset show that our model reduces Frechet inception distance (FID) from 0.041 to 0.015 and improves Top-1 R-Precision from 0.508 to 0.510. Qualitative analysis of pairwise direction similarity between pose codes further confirms the model's controllability for motion editing.
