The popularity of virtual try-on methods has increased in recent years as they allow users to preview the appearance of garments on themselves without physically wearing them. However, existing image-based methods for general virtual try-on provide limited support to synthesize realistic and consistent garment images under different poses, due to two main difficulties: 1) the dataset used to train these methods contains a vast collection of garments, but they lack fine details of each garment; 2) they synthesize results by warping the front-view image of the target garment in a rest pose, which results in poor quality and detail for other viewpoints and poses. To overcome these drawbacks, per-garment virtual try-on methods train garment-specific networks that can produce high-quality results with fine-grained details for a particular target garment. However, existing per-garment virtual try-on methods require the use of a physical measurement garment, which limits their applicability. In this paper, we propose a novel per-garment virtual try-on method that leverages a virtual measurement garment, which eliminates the need for the physical measurement garment, to guide the synthesis of high-quality and temporally consistent garment images under various poses. Furthermore, we introduce a gap-filling module that effectively fills the gap between the synthesized garment and body parts. We conduct qualitative and quantitative evaluations against a state-of-the-art image-based virtual try-on method and ablation studies to demonstrate that our method achieves superior performance in terms of realism and consistency of the generated garment images.

Animations can come to life when they are synchronized with relevant sounds. Yet, synchronizing animations to audio requires tedious key-framing or programming, which is difficult for novice creators. There are existing tools that support audio-driven live animation, but they focus primarily on speech and have little or no support for non-speech sounds. We present SoundToons, an exemplar-based authoring tool for interactive, audio-driven animation focusing on non-speech sounds. Our tool enables novice creators to author live animations to a wide variety of non-speech sounds, such as clapping and instrumental music. We support two types of audio interactions: (1) discrete interaction, which triggers animations when a discrete sound event is detected, and (2) continuous, which synchronizes an animation to continuous audio parameters. By employing an exemplar-based iterative authoring approach, we empower novice creators to design and quickly refine interactive animations. User evaluations demonstrate that novice users can author and perform live audio-driven animation intuitively. Moreover, compared to other input modalities such as trackpads or foot pedals, users preferred using audio as an intuitive way to drive animation.

How to handle gender with machine learning is a controversial topic. A growing critical body of research brought attention to the numerous issues transgender communities face with the adoption of current automatic gender recognition (AGR) systems. In contrast, we explore how such technologies could potentially be appropriated to support transgender practices and needs, especially in non-Western contexts like Japan. We designed a virtual makeup probe to assist transgender individuals with passing, that is to be perceived as the gender they identify as. To understand how such an application might support expressing transgender individuals gender identity or not, we interviewed 15 individuals in Tokyo and found that in the right context and under strict conditions, AGR based systems could assist transgender passing.

Virtual try-on is a promising application of computer graphics and human computer interaction that can have a profound real-world impact especially during this pandemic. Existing image-based works try to synthesize a try-on image from a single image of a target garment, but it inherently limits the ability to react to possible interactions. It is difficult to reproduce the change of wrinkles caused by pose and body size change, as well as pulling and stretching of the garment by hand. In this paper, we propose an alternative per garment capture and synthesis workflow to handle such rich interactions by training the model with many systematically captured images. Our workflow is composed of two parts: garment capturing and clothed person image synthesis. We designed an actuated mannequin and an efficient capturing process that collects the detailed deformations of the target garments under diverse body sizes and poses. Furthermore, we proposed to use a custom-designed measurement garment, and we captured paired images of the measurement garment and the target garments. We then learn a mapping between the measurement garment and the target garments using deep image-to-image translation. The customer can then try on the target garments interactively during online shopping. The proposed workflow requires certain manual labor, but we believe that the cost is acceptable given that the retailers are already paying significant costs for hiring professional photographers and models, stylists, and editors to take photographs for promotion. Our method can remove the need of hiring these costly professionals. We evaluated the effectiveness of the proposed system with ablation studies and quality comparison with previous virtual try-on methods. We perform a user study to show our promising virtual try-on performances. Moreover, we also demonstrate that we use our method for changing virtual costumes in video conferences. Finally, we provide the collected dataset as the cloth dataset parameterized by various viewing angles, body poses, and sizes.

Abstract Generative image modeling techniques such as GAN demonstrate highly convincing image generation result. However, user interaction is often necessary to obtain desired results. Existing attempts add interactivity but require either tailored architectures or extra data. We present a human‐in‐the‐optimization method that allows users to directly explore and search the latent vector space of generative image modelling. Our system provides multiple candidates by sampling the latent vector space, and the user selects the best blending weights within the subspace using multiple sliders. In addition, the user can express their intention through image editing tools. The system samples latent vectors based on inputs and presents new candidates to the user iteratively. An advantage of our formulation is that one can apply our method to arbitrary pre‐trained model without developing specialized architecture or data. We demonstrate our method with various generative image modelling applications, and show superior performance in a comparative user study with prior art iGAN [ZKSE16].