身体性知覚のための深い事前学習
Deep Prior Learning for Embodied Perception
ノイズのあるカメラ姿勢や内部パラメータ、深度といった幾何学的事前情報を活用し、物理スケールを回復するVGGTベースのフレームワークVPGGTを提案。事前情報の希薄化を防ぐパラメータ不要の残差接続と、メートル尺度を予測するグローバルアテンションを導入した。
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: Yimou Wu, Jiaxin Guo, Yun-hui Liu, Zheng Li
分類: cs.CV, cs.RO
原文アブストラクト
Embodied systems need geometric perception that exploits available observations beyond images alone. Recent feed-forward 3D models incorporate geometric priors, including camera poses, intrinsics, and depth. However, handling noisy poses, preserving accurate priors, and recovering physical scale require more than simply accepting these inputs. We introduce \emph{Vision-Prior Geometry Grounded Transformer} (VPGGT), a VGGT-based framework that extends OmniVGGT for prior-aware embodied perception. We formulate sensor-motivated pose corruptions from ground-truth trajectories for training and introduce a parameter-free \emph{prior residual connection} (PRC) to mitigate \emph{prior dilution}, where predictions are less accurate than their supplied pose priors. Our noise formulation targets camera poses; supplied intrinsics and depth receive no additional corruption. We further introduce \emph{Metric Global Attention}, which conditions a global scale token on available pose and depth scales and predicts a shared metric scaling factor for the geometric outputs. Experiments across four datasets show that \emph{PRC} improves translation-direction accuracy and joint pose AUC over a matched training baseline when camera priors are provided for all views, under both exact and corrupted poses. These results support explicit prior access during refinement as a useful addition to feature-level conditioning.
