hand-object pose

17 papers with code • 2 benchmarks • 4 datasets

6D pose estimation of hand and object

Libraries

Use these libraries to find hand-object pose models and implementations

Most implemented papers

HOnnotate: A method for 3D Annotation of Hand and Object Poses

shreyashampali/ho3d CVPR 2020

This dataset is currently made of 77, 558 frames, 68 sequences, 10 persons, and 10 objects.

Learning joint reconstruction of hands and manipulated objects

hassony2/manopth CVPR 2019

Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation.

AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction

zerchen/AlignSDF 26 Jul 2022

We show that such aligned SDFs better focus on reconstructing shape details and improve reconstruction accuracy both for hands and objects.

Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands

wenbowen123/icra20-hand-object-pose 7 Mar 2020

The hand's point cloud is pruned and robust global registration is performed to generate object pose hypotheses, which are clustered.

HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation

bardiadoosti/HOPE CVPR 2020

Hand-object pose estimation (HOPE) aims to jointly detect the poses of both a hand and of a held object.

Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation

shreyashampali/kypt_transformer CVPR 2022

We propose a robust and accurate method for estimating the 3D poses of two hands in close interaction from a single color image.

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

stevenlsw/Semi-Hand-Object CVPR 2021

Estimating 3D hand and object pose from a single image is an extremely challenging problem: hands and objects are often self-occluded during interactions, and the 3D annotations are scarce as even humans cannot directly label the ground-truths from a single image perfectly.

Towards unconstrained joint hand-object reconstruction from RGB videos

hassony2/homan 16 Aug 2021

Our work aims to obtain 3D reconstruction of hands and manipulated objects from monocular videos.

Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing

leolyliu/teg-track 8 Oct 2022

When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose.