arXiv Computer Vision
StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
3d ago
DCGrasp: Distance-aware Controllable Grasp Generation
arXiv:2606.29924v2 Announce Type: replace Abstract: Generating 3D hand-object interactions is essential for applications in robotics, AR/VR, and synthetic data generation, where flexible controllabil...
arXiv Computer Vision
Aug 31
GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image
arXiv:2608.28386v1 Announce Type: new Abstract: Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic o...
arXiv AI
Oct 19
MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping
MANGO‑Grasp introduces an anisotropic interaction framework for cross‑embodiment dexterous grasping. It represents objects as geometry‑oriented 3D Gaussian primitives to preserve local surface geometry, encodes hands with pretrained descriptors that capture morphology and kinematics, and models hand‑object interaction using anisotropic Mahalanobis fields. The method achieves state‑of‑the‑art performance on CMAP and MultiGripperGrasp benchmarks, outperforms baselines by up to 8.24 percentage points in simulation, and demonstrates strong zero‑shot transfer to the unseen SharpaWave hand with up to 16.57 percentage point improvement, achieving 86% success in real‑world experiments.
arXiv AI
Sep 4
Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis
AdaRoboVLG is a Vision‑Language‑Grasp framework that separates a generalizable base grasp policy from task‑specific understanding. The base policy generates and evaluates physically feasible grasp candidates using kinematic mapping and force‑closure stability, while foundation‑model modules supply composable spatial, cognitive, and temporal priors that adapt grasp synthesis to different robotic hands and environments without retraining. Experiments show strong cross‑hand generalization, effective handling of diverse grasping challenges, and functional grasping in cluttered, dynamic settings.
arXiv Computer Vision
Oct 9
OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes
OmniDex presents a large-scale benchmark for dexterous hand grasping, featuring over 2.6 million cluttered scenes and 0.4 B scene-specific grasp ground truths generated via a scalable seed-and-filter strategy. The paper introduces the OmniDex model, which uses Soft Winner-Takes-All learning, human-inspired physical constraints, and physics-driven ranking to address multimodality and precision errors in generative grasp models. Experimental results demonstrate that OmniDex achieves state‑of‑the‑art performance and strong generalization across diverse scenes, views, and unseen objects.
arXiv Computer Vision
Sep 30
DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction
arXiv:2609.36454v1 Announce Type: new Abstract: We study hand-object interaction (HOI) reconstruction from monocular RGB videos, where partial observations can produce visually plausible yet mechanic...