GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image
Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic object reconstruction. Despite plausible body-object configurations, their fingers may float from or penetrate objects instead of forming a grasp. We present GraspHOI, the first framework that reconstructs a full-body 3D HOI from a single image while explicitly optimizing finger articulation against the reconstructed object. GraspHOI recovers object geometry directly, without predefined meshes or a fixed category vocabulary. It reconstructs the b
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “GraspHOI: Full-Body 3D Human-Object Reconstruction with Fing” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzyOverlapping authors or contributors · 62%microsoft/ML-For-Beginners →
“Shared author/contributor keys: shin”
- LinkedLinked via arxiv author · 85%Semin Kim →
“GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image”
- LinkedLinked via arxiv author · 85%Haechan Shin →
“GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image”
- LinkedLinked via arxiv author · 85%Jongyoo Kim →
“GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image”