Interacting Hand-Object Pose Estimation via Dense Mutual Attention

11/16/2022
by   Rong Wang, et al.
0

3D hand-object pose estimation is the key to the success of many computer vision applications. The main focus of this task is to effectively model the interaction between the hand and an object. To this end, existing works either rely on interaction constraints in a computationally-expensive iterative optimization, or consider only a sparse correlation between sampled hand and object keypoints. In contrast, we propose a novel dense mutual attention mechanism that is able to model fine-grained dependencies between the hand and the object. Specifically, we first construct the hand and object graphs according to their mesh structures. For each hand node, we aggregate features from every object node by the learned attention and vice versa for each object node. Thanks to such dense mutual attention, our method is able to produce physically plausible poses with high quality and real-time inference speed. Extensive quantitative and qualitative experiments on large benchmark datasets show that our method outperforms state-of-the-art methods. The code is available at https://github.com/rongakowang/DenseMutualAttention.git.

READ FULL TEXT

page 1

page 7

research
10/21/2022

CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformers

Learning based 6D object pose estimation methods rely on computing large...
research
03/29/2019

DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input

We propose a real-time DNN-based technique to segment hand and object of...
research
08/22/2023

Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views

Hand-object interaction understanding and the barely addressed novel vie...
research
04/27/2022

Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution

Estimating the pose and shape of hands and objects under interaction fin...
research
11/16/2022

Egocentric Hand-object Interaction Detection

In this paper, we propose a method to jointly determine the status of ha...
research
12/02/2020

CPF: Learning a Contact Potential Field to Model the Hand-object Interaction

Estimating hand-object (HO) pose during interaction has been brought rem...
research
08/27/2023

Reconstructing Interacting Hands with Interaction Prior from Monocular Images

Reconstructing interacting hands from monocular images is indispensable ...

Please sign up or login with your details

Forgot password? Click here to reset