GARField: Addressing the visual Sim-to-Real gap in garment manipulation with mesh-attached radiance fields

TL;DR

GARField introduces a differentiable rendering architecture that generates realistic real-world garment observations from simulated mesh states, bridging the sim-to-real gap in textile manipulation for robotic applications.

Contribution

It presents GARField, the first differentiable rendering architecture for generating real-world garment observations from simulated mesh data, enhancing data quality for robotic textile manipulation.

Findings

Enables realistic data generation from simulation

Bridges the sim-to-real gap in garment manipulation

Facilitates better planning and adaptation in robotic textile tasks

Abstract

While humans intuitively manipulate garments and other textile items swiftly and accurately, it is a significant challenge for robots. A factor crucial to human performance is the ability to imagine, a priori, the intended result of the manipulation intents and hence develop predictions on the garment pose. That ability allows us to plan from highly obstructed states, adapt our plans as we collect more information and react swiftly to unforeseen circumstances. Conversely, robots struggle to establish such intuitions and form tight links between plans and observations. We can partly attribute this to the high cost of obtaining densely labelled data for textile manipulation, both in quality and quantity. The problem of data collection is a long-standing issue in data-based approaches to garment manipulation. As of today, generating high-quality and labelled garment manipulation data is mainly attempted through advanced data capture procedures that create simplified state estimations from real-world observations. However, this work proposes a novel approach to the problem by generating real-world observations from object states. To achieve this, we present GARField (Garment Attached Radiance Field), the first differentiable rendering architecture, to our knowledge, for data generation from simulated states stored as triangle meshes. Code is available on https://ddonatien.github.io/garfield-website/