K-Order Graph-oriented Transformer with GraAttention for 3D Pose and Shape Estimation

TL;DR

This paper introduces KOG-Transformer, a novel graph-oriented attention network for 3D pose estimation, and GASE-Net for hand shape modeling, both demonstrating superior performance on benchmark datasets.

Contribution

The paper presents new graph-specific attention modules and a combined network architecture for improved 3D pose and hand shape estimation.

Findings

KOG-Transformer outperforms previous methods on Human3.6M.

GASE-Net accurately predicts hand shapes with strong generalization.

Proposed modules effectively model relationships in graph-structured data.

Abstract

We propose a novel attention-based 2D-to-3D pose estimation network for graph-structured data, named KOG-Transformer, and a 3D pose-to-shape estimation network for hand data, named GASE-Net. Previous 3D pose estimation methods have focused on various modifications to the graph convolution kernel, such as abandoning weight sharing or increasing the receptive field. Some of these methods employ attention-based non-local modules as auxiliary modules. In order to better model the relationship between nodes in graph-structured data and fuse the information of different neighbor nodes in a differentiated way, we make targeted modifications to the attention module and propose two modules designed for graph-structured data, graph relative positional encoding multi-head self-attention (GR-MSA) and K-order graph-oriented multi-head self-attention (KOG-MSA). By stacking GR-MSA and KOG-MSA, we propose a novel network KOG-Transformer for 2D-to-3D pose estimation. Furthermore, we propose a network for shape estimation on hand data, called GraAttention shape estimation network (GASE-Net), which takes a 3D pose as input and gradually models the shape of the hand from sparse to dense. We have empirically shown the superiority of KOG-Transformer through extensive experiments. Experimental results show that KOG-Transformer significantly outperforms the previous state-of-the-art methods on the benchmark dataset Human3.6M. We evaluate the effect of GASE-Net on two public available hand datasets, ObMan and InterHand2.6M. GASE-Net can predict the corresponding shape for input pose with strong generalization ability.