AI Paper Atlas

Research map / 3D vision / 3D generation

Understanding 3D Object Interaction from a Single Image

Shengyi Qian, David F. Fouhey

ICCV 2023 · 3D vision › 3D generation · approach: Hand-object interaction generation · 24 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 transformer with mask decoder instead of ResNet MLP / COHESIV query-point architectures3D object interaction model · 3DOI datasetBox IoU: 28.3 -> 69.9 vs COHESIVImproved
train on real image dataset with annotations rather than synthetic SAPIEN renderings3DADN · 3DOI datasetBox IoU: 5.94 -> 8.53 (3DADN vs SAPIEN)Improved
train on 3DOI dataset instead of human-interaction video dataarticulated object detection · 3DOI datasetArticulation type accuracy: 44.3 -> 89.4Improved
predict affordance from 3DOI-trained model instead of InteractionHotspotsaffordance · 3DOI datasetAffordance SIM: 0.047 -> 0.167Improved
zero-shot transfer to robotics data without finetuning3DOI-trained model · WHIRLBox IoU: 37.1 -> 68.7 vs COHESIVImproved
use dedicated mask decoder for dense predictions3D object interaction model · WHIRLdense predictions (localization, affordance)Improved
use COHESIV instead of ResNet MLP on movable predictionbaseline architectures · 3DOI datasetMovable accuracy: 72.5 -> 71.5Hurt

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