# Learning joint reconstruction of hands and manipulated objects

## TL;DR

This paper introduces a learnable model for joint hand-object reconstruction during manipulation, utilizing a novel contact loss and a large synthetic dataset, improving grasp quality from RGB images.

## Contribution

It proposes a new end-to-end model with a contact loss for physically plausible hand-object reconstruction and introduces the ObMan dataset for training and evaluation.

## Key findings

- Improved grasp quality metrics over baselines.
- Effective transfer of synthetic-trained models to real data.
- Demonstrated the benefit of manipulation constraints in reconstruction.

## Abstract

Estimating hand-object manipulations is essential for interpreting and imitating human actions. Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation. Yet, reconstructing hands and objects during manipulation is a more challenging task due to significant occlusions of both the hand and object. While presenting challenges, manipulations may also simplify the problem since the physics of contact restricts the space of valid hand-object configurations. For example, during manipulation, the hand and object should be in contact but not interpenetrate. In this work, we regularize the joint reconstruction of hands and objects with manipulation constraints. We present an end-to-end learnable model that exploits a novel contact loss that favors physically plausible hand-object constellations. Our approach improves grasp quality metrics over baselines, using RGB images as input. To train and evaluate the model, we also propose a new large-scale synthetic dataset, ObMan, with hand-object manipulations. We demonstrate the transferability of ObMan-trained models to real data.