Real‐time Virtual‐Try‐On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers. (24th May 2022)

• Record Type: Journal Article
• Authors: Kips, R.; Jiang, R.; Ba, S.; Duke, B.; Perrot, M.; Gori, P.; Bloch, I.
• Is Part Of: Computer graphics forum. Volume 41:Number 2(2022)
• Page Start: 29
• Page End: 40
• Publication Date: 2022-05-24
• Subjects: CCS Concepts -- Computing methodologies → Computer vision -- Machine learning -- Computer graphics; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.14456
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: Augmented reality applications have rapidly spread across online retail platforms and social media, allowing consumers to virtually try‐on a large variety of products, such as makeup, hair dying, or shoes. However, parametrizing a renderer to synthesize realistic images of a given product remains a challenging task that requires expert knowledge. While recent work has introduced neural rendering methods for virtual try‐on from example images, current approaches are based on large generative models that cannot be used in real‐time on mobile devices. This calls for a hybrid method that combines the advantages of computer graphics and neural rendering approaches. In this paper, we propose a novel framework based on deep learning to build a real‐time inverse graphics encoder that learns to map a single example image into the parameter space of a given augmented reality rendering engine. Our method leverages self‐supervised learning and does not require labeled training data, which makes it extendable to many virtual try‐on applications. Furthermore, most augmented reality renderers are not differentiable in practice due to algorithmic choices or implementation constraints to reach real‐time on portable devices. To relax the need for a graphics‐based differentiable renderer in inverse graphics problems, we introduce a trainable imitator module. Our imitator is a generative network that learns to accurately reproduce the behavior of a given non‐differentiable renderer. We propose a novel rendering sensitivity loss to train the imitator, which ensures that the network learns an accurate and continuous representation for each rendering parameter. Automatically learning a differentiable renderer, as proposed here, could be beneficial for various inverse graphics tasks. Our framework enables novel applications where consumers can virtually try‐on a novel unknown product from an inspirational reference image on social media. It can also be used by computer graphics artists to automatically create realistic rendering from a reference product image.