Towards unconstrained joint hand-object reconstruction from RGB videos

TL;DR

This paper introduces a learning-free method for 3D reconstruction of hands and objects from monocular videos, enabling applications in robotics and human demonstration analysis without requiring 3D supervision.

Contribution

It presents a novel fitting approach that handles two-hand object interactions without supervised training, unlike previous methods that depend on 3D ground truth data.

Findings

Effective on datasets with varying difficulty levels

Does not require 3D supervision or training data

Handles two-hand object interactions seamlessly

Abstract

Our work aims to obtain 3D reconstruction of hands and manipulated objects from monocular videos. Reconstructing hand-object manipulations holds a great potential for robotics and learning from human demonstrations. The supervised learning approach to this problem, however, requires 3D supervision and remains limited to constrained laboratory settings and simulators for which 3D ground truth is available. In this paper we first propose a learning-free fitting approach for hand-object reconstruction which can seamlessly handle two-hand object interactions. Our method relies on cues obtained with common methods for object detection, hand pose estimation and instance segmentation. We quantitatively evaluate our approach and show that it can be applied to datasets with varying levels of difficulty for which training data is unavailable.