computer-vision-7

hand-object pose

3260 papers • 126 benchmarks • 313 datasets

6D pose estimation of hand and object

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in hand-object-pose-15

Trend

Dataset

Best Model

Actions

DexYCB

HO-3D

Libraries

i

Use these libraries to find hand-object-pose-15 models and implementations

rongakowang/densemutualattention

2 papers 31

Datasets

DexYCB

ARCTIC

Human Palm and Gloves Dataset | Human Body Parts Dataset

Subtasks

No subtasks available.

Most implemented papers

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

Markus Oberweger, V. Lepetit, Shreyas Hampali, Mahdi Rad•Mon Jul 01 2019

We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. Our motivation is the current lack of annotated real images for this problem, as estimating the 3D poses is challenging, mostly because of the mutual occlusions between the hand and the object. To tackle this challenge, we capture sequences with one or several RGB-D cameras and jointly optimize the 3D hand and object poses over all the frames simultaneously. This method allows us to automatically annotate each frame with accurate estimates of the poses, despite large mutual occlusions. With this method, we created HO-3D, the first markerless dataset of color images with 3D annotations for both the hand and object. This dataset is currently made of 77,558 frames, 68 sequences, 10 persons, and 10 objects. Using our dataset, we develop a single RGB image-based method to predict the hand pose when interacting with objects under severe occlusions and show it generalizes to objects not seen in the dataset.

Content

451 0

Paper Graph

Learning Joint Reconstruction of Hands and Manipulated Objects

Gül Varol, I. Laptev, Michael J. Black, C. Schmid, Dimitrios Tzionas, Yana Hasson, Igor Kalevatykh•Wed Apr 10 2019

This work presents an end-to-end learnable model that exploits a novel contact loss that favors phys- ically plausible hand-object constellations, and improves grasp quality metrics over baselines, using RGB images as input.

608 0

Paper Graph

ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis

Cewu Lu, Wenqiang Xu, Jiefeng Li, Jun Lv, Lixin Yang, Kailin Li, Xinyu Zhan•Sat Sep 11 2021

This work proposes ArtiBoost, a lightweight online data enhancement method that performs data exploration and synthesis within a learning pipeline, and those synthetic data are blended into real-world source data for training.

106 0

Paper Graph

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

Bowen Wen, Chaitanya Mitash, Kostas E. Bekris, Sruthi Soorian, A. Kimmel, A. Sintov•Fri Mar 06 2020

A depth-based framework for robust pose estimation and short response times for adaptive hands, which demonstrates the accuracy and computational efficiency of the framework when applied on challenging, highly-occluded scenarios for different object types.

52 0

Paper Graph

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

David J. Crandall, Bardia Doosti, Shujon Naha, Majid Mirbagheri•Mon Mar 30 2020

A lightweight model called HOPE-Net is proposed which jointly estimates hand and object pose in 2D and 3D in real-time and could be applied to other 3D landmark detection problems, where it is possible to first predict the 2D keypoints and then transform them to 3D.

219 0

Paper Graph

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

V. Lepetit, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar•Wed Apr 28 2021

This work proposes a robust and accurate method for estimating the 3D poses of two hands in close interaction from a single color image by relying on a CNN to first localize joints as 2D keypoints, and on self-attention between the CNN features at these keypoints to associate them with the corresponding hand joint.

163 0

Paper Graph

Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos

Gül Varol, I. Laptev, C. Schmid, Yana Hasson•Sun Aug 15 2021

This work proposes a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions and shows that it can be applied to datasets with varying levels of difficulty for which training data is unavailable.

76 0

Paper Graph

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

I. Laptev, C. Schmid, Yana Hasson, Zerui Chen•Mon Jul 25 2022

This work aims to improve SDF models using priors provided by parametric representations and proposes a joint learning framework that disentangles the pose and the shape and shows that such aligned SDFs better focus on reconstructing shape details and improve reconstruction accuracy both for hands and objects.

79 0

Paper Graph

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

Li Yi, Yun Liu, Xiaomeng Xu, Weihang Chen, Hao Yuan, He Wang, Jing Xu, Rui Chen•Fri Oct 07 2022

TEG-Track is introduced, a tactile-enhanced 6D pose tracking system that can track previously unseen objects held in hand that consistently enhances state-of-the-art generalizable 6D pose trackers in synthetic and real-world scenarios.

23 0

Paper Graph

A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?

Théo Morales, G. Lacey•Sun Oct 30 2022

A novel benchmark for object group distribution shifts in hand and object pose regression for object grasping is proposed and the hypothesis that meta-learning a baseline pose regression neural network can adapt to these shifts and generalize better to unknown objects is tested.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.