Newest papers

DenseHap: Dense Hand Haptic Estimation from Monocular Images

Junhan Xue, Rolandos Alexandros Potamias · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26583 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

À medida que a manipulação robótica habilidosa do código avança, as anotações escaláveis das interações mão-objeto humano estão se tornando cada vez mais importantes. Além disso, os métodos anteriores de estimativa de contato com a mão sofreram de problemas como falhas de classificação do lado dorsal e precisão insuficiente, ao mesmo tempo em que falta um quadro unificado para integrar múltiplas modalidades de interação mão-ambiente, incluindo campos de distância, limiares de contato e pressão. Para resolver isso, apresentamos DenseHap, uma abordagem unificada de ponta a ponta para estimar o reconhecimento de distância de campo de mão, detecção de contato com a mão abrangente, análise de pressão da mão e reconstrução da mão de uma única imagem monocular. Ao incorporar três cabeças

Machine translation (Meta M2M100); the English original follows.

Abstract

As dexterous robotic manipulation advances, scalable annotations of human hand-object interactions are becoming increasingly important. Furthermore, previous hand contact estimation methods suffered from issues such as dorsal-side misclassifications and insufficient precision, while lacking a unified framework for integrating multiple hand to environment interaction modalities, including distance fields, contact thresholds, and pressure. To address that, we present DenseHap, a unified end-to-end approach to estimate hand distance field recognition, comprehensive hand contact detection, hand pressure analysis, and hand reconstruction from a single monocular image. By incorporating three distinctly defined heads, along with a pretrained 3D reconstructed skeleton and an enhanced dataset, DenseHap outperforms previous state of the art models on four evaluation datasets, improving the F1 score by 8.5 percentage points (a 16% relative improvement) on untrained datasets and by 3 percentage points (5% relative improvement) on in-distribution datasets. Furthermore, DenseHap has effectively improved short-range hand estimate and pressure evaluation. Code and models will be publicly available upon the paper's acceptance.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Monocular, Artificial intelligence, Computer science, Computer vision, Haptic technology, Scalability

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26583, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange