Browsing by Author "Wang, Zeyu"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    DASKEL: An Interactive Choreographical System with Labanotation-Skeleton Translation
    (The Eurographics Association, 2023) Luo, Siyuan; Yu, Borou; Wang, Zeyu; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.
    We propose DASKEL, a real-time interactive choreography system with bidirectional human skeleton-Labanotation conversion. DASKEL fuses dance notation (DA) with human skeleton data (SKEL). Our approach connects dance data represented in Labanotation with motion capture skeleton data in BVH format, facilitating seamless bidirectional conversion between the two formats. Moreover, DASKEL introduces a numerical representation for symbols used in Labanotation and supports their intuitive visualization which augments the practicality and applicability. Previous methods for the conversion between Labanotation and human skeleton only support the upper body, and our approach generalizes to the bidirectional conversion for the whole body. To generate more accurate and human-like dance postures, we integrate kinematic methods with physics-based simulation, resulting in more natural character animations generated from dance notations.
  • No Thumbnail Available
    Item
    Is Drawing Order Important?
    (The Eurographics Association, 2023) Qiu, Sherry; Wang, Zeyu; McMillan, Leonard; Rushmeier, Holly; Dorsey, Julie; Babaei, Vahid; Skouras, Melina
    The drawing process is crucial to understanding the final result of a drawing. There has been a long history of understanding human drawing; what kinds of strokes people use and where they are placed. An area of interest in Artificial Intelligence is developing systems that simulate human behavior in drawing. However, there has been little work done to understand the order of strokes in the drawing process. Without sufficient understanding of natural drawing order, it is difficult to build models that can generate natural drawing processes. In this paper, we present a study comparing multiple types of stroke orders to confirm findings from previous work and demonstrate that multiple orderings of the same set of strokes can be perceived as human-drawn and different stroke order types achieve different perceived naturalness depending on the type of image prompt.
  • Thumbnail Image
    Item
    Learning a Style Space for Interactive Line Drawing Synthesis from Animated 3D Models
    (The Eurographics Association, 2022) Wang, Zeyu; Wang, Tuanfeng Y.; Dorsey, Julie; Yang, Yin; Parakkat, Amal D.; Deng, Bailin; Noh, Seung-Tak
    Most non-photorealistic rendering (NPR) methods for line drawing synthesis operate on a static shape. They are not tailored to process animated 3D models due to extensive per-frame parameter tuning needed to achieve the intended look and natural transition. This paper introduces a framework for interactive line drawing synthesis from animated 3D models based on a learned style space for drawing representation and interpolation. We refer to style as the relationship between stroke placement in a line drawing and its corresponding geometric properties. Starting from a given sequence of an animated 3D character, a user creates drawings for a set of keyframes. Our system embeds the raster drawings into a latent style space after they are disentangled from the underlying geometry. By traversing the latent space, our system enables a smooth transition between the input keyframes. The user may also edit, add, or remove the keyframes interactively, similar to a typical keyframe-based workflow. We implement our system with deep neural networks trained on synthetic line drawings produced by a combination of NPR methods. Our drawing-specific supervision and optimization-based embedding mechanism allow generalization from NPR line drawings to user-created drawings during run time. Experiments show that our approach generates high-quality line drawing animations while allowing interactive control of the drawing style across frames.
  • Thumbnail Image
    Item
    A Low-Dimensional Perceptual Space for Intuitive BRDF Editing
    (The Eurographics Association, 2021) Shi, Weiqi; Wang, Zeyu; Soler, Cyril; Rushmeier, Holly; Bousseau, Adrien and McGuire, Morgan
    Understanding and characterizing material appearance based on human perception is challenging because of the highdimensionality and nonlinearity of reflectance data. We refer to the process of identifying specific characteristics of material appearance within the same category as material estimation, in contrast to material categorization which focuses on identifying inter-category differences [FNG15]. In this paper, we present a method to simulate the material estimation process based on human perception. We create a continuous perceptual space for measured tabulated data based on its underlying low-dimensional manifold. Unlike many previous works that only address individual perceptual attributes (such as gloss), we focus on extracting all possible dimensions that can explain the perceived differences between appearances. Additionally, we propose a new material editing interface that combines image navigation and sliders to visualize each perceptual dimension and facilitate the editing of tabulated BRDFs. We conduct a user study to evaluate the efficacy of the perceptual space and the interface in terms of appearance matching.
  • Thumbnail Image
    Item
    Reconstructing Dura-Europos From Sparse Photo Collections Using Deep Contour Extraction
    (The Eurographics Association, 2021) Shen, Yifei; Wang, Zeyu; Sun, Qinying; Chen, Anne; Rushmeier, Holly; Hulusic, Vedad and Chalmers, Alan
    In this short paper we present work in progress on creating tools to facilitate 3D reconstruction of cultural heritage. We propose three new types of tools to make reconstruction easier - first we fetch linked open data to help organize source materials, next we extract key contours from photographs to speed up reconstruction, and finally we generate video tours of positioned photos and sketches. We also introduce a new, expanded 3D software system to support these tasks. The system is developed based on previous work on 3D sketching in the context of cultural heritage documentation, in particular CHER-ish. We demonstrate the potential of these tools by describing results obtained from the Dura-Europos data set.