AI Paper Atlas

Research map / 3D vision / 3D generation

Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation

Tim Engelbracht, René Zurbrügg, Matteo Wohlrapp, Martin Büchner, Abhinav Valada, Marc Pollefeys, Hermann Blum, Zuria Bauer

CVPR 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use projected (motion-aligned) forces instead of raw force-torque readings (ablation)ForceSight zero-shot · Hoi! visual force estimationforce RMSE (N): 2.57 -> 2.23Improved
evaluate ForceSight on Hoi! instead of its original datasetForceSight · force RMSEforce RMSE (N): 0.404 -> 2.57Hurt
use DINOv2 instead of DINO decoder (ablation)Sparsh · Hoi! tactile force estimationcombined force RMSE (N): 3.86 -> 4.11Hurt
move from lab/controlled to in-the-wild settingArtiPoint · articulation estimation (Arti4D vs Hoi!)prismatic axis angle error (deg): 14.54 -> 47.06Hurt
use GPT-5 for articulation type prediction from single RGB viewarticulation type recognition · Hoi! articulation estimationrevolute type recall (%): 57.10 -> 89.7Improved
use exocentric instead of egocentric view for GPT-5 (ablation)GPT-5 · Hoi! articulation estimationprismatic type recall (%): 71.9 -> 65.6Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy