EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

TL;DR

EasyHOI leverages large foundational models and a prior-guided optimization scheme to reconstruct diverse hand-object interactions from single images, outperforming existing methods in accuracy and robustness.

Contribution

The paper introduces a novel pipeline combining large models and prior-guided optimization for single-view hand-object interaction reconstruction, addressing challenges of ambiguity and occlusion.

Findings

Outperforms baseline methods across multiple datasets.

Faithfully reconstructs diverse hand-object interactions.

Utilizes large models for robust initial estimates.

Abstract

Our work aims to reconstruct hand-object interactions from a single-view image, which is a fundamental but ill-posed task. Unlike methods that reconstruct from videos, multi-view images, or predefined 3D templates, single-view reconstruction faces significant challenges due to inherent ambiguities and occlusions. These challenges are further amplified by the diverse nature of hand poses and the vast variety of object shapes and sizes. Our key insight is that current foundational models for segmentation, inpainting, and 3D reconstruction robustly generalize to in-the-wild images, which could provide strong visual and geometric priors for reconstructing hand-object interactions. Specifically, given a single image, we first design a novel pipeline to estimate the underlying hand pose and object shape using off-the-shelf large models. Furthermore, with the initial reconstruction, we employ a prior-guided optimization scheme, which optimizes hand pose to comply with 3D physical constraints and the 2D input image content. We perform experiments across several datasets and show that our method consistently outperforms baselines and faithfully reconstructs a diverse set of hand-object interactions. Here is the link of our project page: https://lym29.github.io/EasyHOI-page/