QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects

TL;DR

QORT-Former is a novel real-time Transformer framework that efficiently estimates 3D poses of two hands and an object, significantly improving accuracy and speed for AR/VR applications.

Contribution

This paper introduces the first real-time Transformer-based framework for 3D hand-object pose estimation, optimizing queries and decoders for enhanced accuracy and efficiency.

Findings

Achieved 53.5 FPS on RTX 3090TI GPU.

Surpassed state-of-the-art accuracy on H2O and FPHA datasets.

Set new benchmarks in interaction recognition accuracy.

Abstract

Significant advancements have been achieved in the realm of understanding poses and interactions of two hands manipulating an object. The emergence of augmented reality (AR) and virtual reality (VR) technologies has heightened the demand for real-time performance in these applications. However, current state-of-the-art models often exhibit promising results at the expense of substantial computational overhead. In this paper, we present a query-optimized real-time Transformer (QORT-Former), the first Transformer-based real-time framework for 3D pose estimation of two hands and an object. We first limit the number of queries and decoders to meet the efficiency requirement. Given limited number of queries and decoders, we propose to optimize queries which are taken as input to the Transformer decoder, to secure better accuracy: (1) we propose to divide queries into three types (a left hand query, a right hand query and an object query) and enhance query features (2) by using the contact information between hands and an object and (3) by using three-step update of enhanced image and query features with respect to one another. With proposed methods, we achieved real-time pose estimation performance using just 108 queries and 1 decoder (53.5 FPS on an RTX 3090TI GPU). Surpassing state-of-the-art results on the H2O dataset by 17.6% (left hand), 22.8% (right hand), and 27.2% (object), as well as on the FPHA dataset by 5.3% (right hand) and 10.4% (object), our method excels in accuracy. Additionally, it sets the state-of-the-art in interaction recognition, maintaining real-time efficiency with an off-the-shelf action recognition module.