AI Paper Atlas

Research map / 3D vision / Human pose estimation

SpatialHand: Generative Object Manipulation from 3D Prespective

Zehan Wang, Jialei Wang, Siyu Chen, Ziang Zhang, Luping Liu, Xize Cheng, Kaihang Pan, Hengshuang Zhao, Zhou Zhao

ICLR 2026 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression

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
add textual caption to visual reference (ablation)SpatialHand · 3D-aware insertionDINO: 78.8 -> 81.7Improved
add textual caption to visual reference (ablation)SpatialHand · 3D-aware insertionAcc@30: 46.8 -> 52.0Improved
add textual caption to visual reference (ablation)SpatialHand · 3D-aware insertionAbsRel: 18.5 -> 19.8Hurt
add geometry-aware composition (ablation)SpatialHand · 3D-aware insertionAbsRel: 25.5 -> 19.8Improved
add geometry-aware composition (ablation)SpatialHand · 3D-aware insertionDINO: 80.2 -> 81.7Improved
add geometry-aware composition (ablation)SpatialHand · 3D-aware insertionAcc@30: 48.8 -> 52.0Improved
add stage 1 novel view synthesis fine-tuning (ablation)SpatialHand · 3D-aware insertionAcc@30: 28.7 -> 52.0Improved
add stage 1 novel view synthesis fine-tuning (ablation)SpatialHand · 3D-aware insertionDINO: 79.8 -> 81.7Improved
add stage 1 novel view synthesis fine-tuning (ablation)SpatialHand · 3D-aware insertionAbsRel: 18.2 -> 19.8No clear effect
use SpatialHand pose conditions instead of GPT-4o text instructionsSpatialHand vs GPT-4o · 3D-aware insertion (visual+textual)Acc@30: 20.2 -> 52.0Improved
use SpatialHand pose conditions instead of GPT-4o text instructionsSpatialHand vs GPT-4o · 3D-aware insertion (visual+textual)AbsRel: 38.6 -> 19.8Improved
use SpatialHand instead of GPT-4o for occlusion movementSpatialHand vs GPT-4o · 3D-aware movement (occlusion)VLM-Acc: 59.5 -> 82.6Improved

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