Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction

TL;DR

This paper introduces DHANet, a novel hyperbolic space-based method for detailed 3D hand-object reconstruction from a single RGB image, outperforming existing Euclidean space approaches.

Contribution

The paper presents the first precise hand-object reconstruction method in hyperbolic space, leveraging hyperbolic geometry for improved feature learning and interaction modeling.

Findings

Outperforms most state-of-the-art methods on three datasets.

Utilizes hyperbolic space to better preserve mesh geometric properties.

Introduces dynamic hyperbolic graph convolution and image-attention hyperbolic graph convolution modules.

Abstract

Reconstructing both objects and hands in 3D from a single RGB image is complex. Existing methods rely on manually defined hand-object constraints in Euclidean space, leading to suboptimal feature learning. Compared with Euclidean space, hyperbolic space better preserves the geometric properties of meshes thanks to its exponentially-growing space distance, which amplifies the differences between the features based on similarity. In this work, we propose the first precise hand-object reconstruction method in hyperbolic space, namely Dynamic Hyperbolic Attention Network (DHANet), which leverages intrinsic properties of hyperbolic space to learn representative features. Our method that projects mesh and image features into a unified hyperbolic space includes two modules, ie. dynamic hyperbolic graph convolution and image-attention hyperbolic graph convolution. With these two modules, our method learns mesh features with rich geometry-image multi-modal information and models better hand-object interaction. Our method provides a promising alternative for fine hand-object reconstruction in hyperbolic space. Extensive experiments on three public datasets demonstrate that our method outperforms most state-of-the-art methods.