robots-4

Grasp Contact Prediction

3260 papers • 126 benchmarks • 313 datasets

Predict contact between object and hand (human or robot).

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in grasp-contact-prediction-9

Trend

Dataset

Best Model

Actions

ContactDB

ContactPose

Libraries

i

Use these libraries to find grasp-contact-prediction-9 models and implementations

Datasets

GRAB

ContactDB

ContactPose

A Billion Ways to Grasp

GAS

Subtasks

No subtasks available.

Most implemented papers

ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging

James Hays, Samarth Brahmbhatt, Cusuh Ham, C. Kemp•Sun Apr 14 2019

This work presents ContactDB, a novel dataset of contact maps for household objects that captures the rich hand-object contact that occurs during grasping, enabled by use of a thermal camera.

246

Content

0

Paper Graph

ContactPose: A Dataset of Grasps with Object Contact and Hand Pose

James Hays, Samarth Brahmbhatt, C. Kemp, Chengcheng Tang, Christopher D. Twigg•Sat Jul 18 2020

This work introduces ContactPose, the first dataset of hand-object contact paired with hand pose, object pose, and RGB-D images, and uses this data to rigorously evaluate various data representations, heuristics from the literature, and learning methods for contact modeling.

256 0

Paper Graph

GRAB: A Dataset of Whole-Body Human Grasping of Objects

Michael J. Black, Dimitrios Tzionas, N. Ghorbani, Omid Taheri•Mon Aug 24 2020

This work collects a new dataset, called GRAB (GRasping Actions with Bodies), of whole-body grasps, containing full 3D shape and pose sequences of 10 subjects interacting with 51 everyday objects of varying shape and size, and trains GrabNet, a conditional generative network, to predict 3D handgrasps for unseen 3D object shapes.

470 0

Paper Graph

CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulation

Bowen Wen, Kostas E. Bekris, S. Schaal, Wenzhao Lian•Sat Sep 18 2021

A novel, object-centric canonical representation at the category level is proposed, which allows establishing dense correspondence across object instances and transferring task-relevant grasps to novel instances.

97 0

Paper Graph

Adding a benchmark result helps the community track progress.