LESSでより多くを実現:触覚イメージングのための局所シーン表現
More with LESS -- Local Scene Representations for Tactile Imaging
触覚イメージングのための物体中心の局所表現(LESS)を提案し、局所受容野を持つリカレントエンコーダのグリッドで触覚シーンをモデル化することで、汎化性能を高め、手持ちセンシングや3D再構成を可能にした。
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: Zohar Rimon, Elisei Shafer, Tal Tepper, Daniel Kozin, Alon Malka, Roy Holland, Aviv Tamar
分類: cs.LG
原文アブストラクト
Tactile imaging seeks to reconstruct the internal structure of soft objects through touch sensing, with applications in medical diagnosis and robotic manipulation. Recent self-supervised learning approaches have shown promising results, but rely on global, unstructured representations and robot-controlled sensing, limiting generalization and practical use. We propose Local Encoder for Spatial Sensing (LESS), an object-centric tactile representation that exploits the local nature of touch. The tactile scene is modeled as a grid of recurrent encoders with local receptive fields, whose states are fused to reconstruct 2D or 3D images of internal structure. This compositional design enables strong generalization: models trained on single-inclusion phantoms accurately image objects with multiple inclusions and varying sizes. The local structure further supports spatial uncertainty estimation. In addition, we enable hand-held tactile imaging via external pose tracking and human-like palpation data, and extend tactile imaging to full 3D reconstruction.
