FreeAction: 学習不要で軌道から動画生成の忠実度を高める手法
FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video Generation
拡散モデルによるロボット動画生成で、行動パラメータを活用してガイダンス強度とノイズ初期化を調整する学習不要の推論時手法を提案し、動作の一貫性と画質を改善した。
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: Seungwook Kim, Seunghyeon Lee, Minsu Cho
分類: cs.CV, cs.RO
原文アブストラクト
Generating realistic robot videos from explicit action trajectories is a critical step toward building effective world models and robotics foundation models. We introduce two training-free, inference-time techniques that fully exploit explicit action parameters in diffusion-based robot video generation. Instead of treating action vectors as passive conditioning signals, our methods actively incorporate them to guide both the classifier-free guidance process and the initialization of Gaussian latents. First, action-scaled classifier-free guidance dynamically modulates guidance strength in proportion to action magnitude, enhancing controllability over motion intensity. Second, action-scaled noise truncation adjusts the distribution of initially sampled noise to better align with the desired motion dynamics. Experiments on real robot manipulation datasets demonstrate that these techniques significantly improve action coherence and visual quality across diverse robot environments.
