読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニュースクイックテイク1 分で読めるDisconfirmAI 編集部

EgoPHI estimates hand-object contact and 3D force from one RGB image

EgoPHI jointly estimates dense contact maps and 3D force distributions for hand and object meshes from a single RGB image and object geometry, using physics simulation for per-vertex force supervision, with real validation on only two objects and eight participants.

検証済み 2026-09-17 13:39 GMT+8

You can now jointly estimate dense contact maps and 3D force distributions for hand and object meshes from a single RGB image and object geometry: EgoPHI uses physics simulation to generate per-vertex force supervision, with real-world validation on only two objects and eight participants.

Previously there was no method to obtain both contact and 3D force distributions from monocular RGB, and per-vertex force supervision was hard to collect directly.

Andela Ilic, Christian Holz and co-authors released EgoPHI on arXiv (submitted August 13, revised to v2 on September 15); the page notes acceptance to ECCV 2026.

No independent verification yet. Source: arXiv:2608.13014 abstract page ↗

ソース

  • arxiv.org↗
リサーチを続ける →
ログイン / 新規登録
読書リサーチレーダー投資フレームワーク