Pacific Graphics 2022 - Short Papers, Posters, and Work-in-Progress Papers
Kyoto, Japan | October 5 – 8, 2022

(for Full Papers (CGF) see PG 2022 - CGF 41-7)


Sketch and Modeling
Learning a Style Space for Interactive Line Drawing Synthesis from Animated 3D Models
Zeyu Wang, Tuanfeng Y. Wang, and Julie Dorsey
Multi-instance Referring Image Segmentation of Scene Sketches based on Global Reference Mechanism
Peng Ling, Haoran Mo, and Chengying Gao
Human Face Modeling based on Deep Learning through Line-drawing
Yuta Kawanaka, Syuhei Sato, Kaisei Sakurai, Shangce Gao, and Zheng Tang
An Interactive Modeling System of Japanese Castles with Decorative Objects
Shogo Umeyama and Yoshinori Dobashi
Interactive Deformable Image Registration with Dual Cursor
Takeo Igarashi, Tsukasa Koike, and Taichi Kin
Fast Geometric Computation
Intersection Distance Field Collision for GPU
Bastian Krayer, Rebekka Görge, and Stefan Müller
Reconstructing Bounding Volume Hierarchies from Memory Traces of Ray Tracers
Max von Buelow, Tobias Stensbeck, Volker Knauthe, Stefan Guthe, and Dieter W. Fellner
Rendering - Sampling
Improving View Independent Rendering for Multiview Effects
Ajinkya Gavane and Benjamin Watson
Image Enhancement
Adaptive and Dynamic Regularization for Rolling Guidance Image Filtering
Miku Fukatsu, Shin Yoshizawa, Hiroshi Takemura, and Hideo Yokota
Image Restoration
Shadow Removal via Cascade Large Mask Inpainting
Juwan Kim, Seung-Heon Kim, and Insung Jang
Perception and Visualization
Aesthetic Enhancement via Color Area and Location Awareness
Bailin Yang, Qingxu Wang, Frederick W. B. Li, Xiaohui Liang, Tianxiang Wei, and Changrui Zhu
DARC: A Visual Analytics System for Multivariate Applicant Data Aggregation, Reasoning and Comparison
Yihan Hou, Yu Liu, He Wang, Zhichao Zhang, Yue Li, Hai-Ning Liang, and Lingyun Yu
Digital Human
DFGA: Digital Human Faces Generation and Animation from the RGB Video using Modern Deep Learning Technology
Diqiong Jiang, Lihua You, Jian Chang, and Ruofeng Tong

Recent Submissions

  • DFGA: Digital Human Faces Generation and Animation from the RGB Video using Modern Deep Learning Technology 

    Jiang, Diqiong; You, Lihua; Chang, Jian; Tong, Ruofeng (The Eurographics Association, 2022)
    High-quality and personalized digital human faces have been widely used in media and entertainment, from film and game production to virtual reality. However, the existing technology of generating digital faces requires ...
  • DARC: A Visual Analytics System for Multivariate Applicant Data Aggregation, Reasoning and Comparison 

    Hou, Yihan; Liu, Yu; Wang, He; Zhang, Zhichao; Li, Yue; Liang, Hai-Ning; Yu, Lingyun (The Eurographics Association, 2022)
    People often make decisions based on their comprehensive understanding of various materials, judgement of reasons, and comparison among choices. For instance, when hiring committees review multivariate applicant data, they ...
  • Adaptive and Dynamic Regularization for Rolling Guidance Image Filtering 

    Fukatsu, Miku; Yoshizawa, Shin; Takemura, Hiroshi; Yokota, Hideo (The Eurographics Association, 2022)
    Separating shapes and textures of digital images at different scales is useful in computer graphics. The Rolling Guidance (RG) filter, which removes structures smaller than a specified scale while preserving salient edges, ...
  • Aesthetic Enhancement via Color Area and Location Awareness 

    Yang, Bailin; Wang, Qingxu; Li, Frederick W. B.; Liang, Xiaohui; Wei, Tianxiang; Zhu, Changrui (The Eurographics Association, 2022)
    Choosing a suitable color palette can typically improve image aesthetic, where a naive way is choosing harmonious colors from some pre-defined color combinations in color wheels. However, color palettes only consider the ...
  • Shadow Removal via Cascade Large Mask Inpainting 

    Kim, Juwan; Kim, Seung-Heon; Jang, Insung (The Eurographics Association, 2022)
    We present a novel shadow removal framework based on the image inpainting approach. The proposed method consists of two cascade Large-Mask inpainting(LaMa) networks for shadow inpainting and edge inpainting. Experiments ...
  • Improving View Independent Rendering for Multiview Effects 

    Gavane, Ajinkya; Watson, Benjamin (The Eurographics Association, 2022)
    This paper describes improvements to view independent rendering (VIR) that make it much more useful for multiview effects. Improved VIR's (iVIR's) soft shadows are nearly identical in quality to VIR's and produced with ...
  • Reconstructing Bounding Volume Hierarchies from Memory Traces of Ray Tracers 

    Buelow, Max von; Stensbeck, Tobias; Knauthe, Volker; Guthe, Stefan; Fellner, Dieter W. (The Eurographics Association, 2022)
    The ongoing race to improve computer graphics leads to more complex GPU hardware and ray tracing techniques whose internal functionality is sometimes hidden to the user. Bounding volume hierarchies and their construction ...
  • Intersection Distance Field Collision for GPU 

    Krayer, Bastian; Görge, Rebekka; Müller, Stefan (The Eurographics Association, 2022)
    We present a framework for finding collision points between objects represented by signed distance fields. Particles are used to sample the region where intersections can occur. The distance field representation is used ...
  • Interactive Deformable Image Registration with Dual Cursor 

    Igarashi, Takeo; Koike, Tsukasa; Kin, Taichi (The Eurographics Association, 2022)
    Deformable image registration is the process of deforming a target image to match corresponding features of a reference image. Fully automatic registration remains difficult; thus, manual registration is dominant in practice. ...
  • An Interactive Modeling System of Japanese Castles with Decorative Objects 

    Umeyama, Shogo; Dobashi, Yoshinori (The Eurographics Association, 2022)
    We present an interactive modeling system for Japanese castles. We develop an user interface that can generate the fundamental structure of the castle tower consisting of stone walls, turrets, and roofs. By clicking on the ...
  • Human Face Modeling based on Deep Learning through Line-drawing 

    Kawanaka, Yuta; Sato, Syuhei; Sakurai, Kaisei; Gao, Shangce; Tang, Zheng (The Eurographics Association, 2022)
    This paper presents a deep learning-based method for creating 3D human face models. In recent years, several sketch-based shape modeling methods have been proposed. These methods allow the user to easily model various ...
  • Multi-instance Referring Image Segmentation of Scene Sketches based on Global Reference Mechanism 

    Ling, Peng; Mo, Haoran; Gao, Chengying (The Eurographics Association, 2022)
    Scene sketch segmentation based on referring expression plays an important role in sketch editing of anime industry. While most existing referring image segmentation approaches are designed for the standard task of generating ...
  • Pacific Graphics 2022 - Short Papers, Posters, and Work-in-Progress Papers: Frontmatter 

    Yang, Yin; Parakkat, Amal D.; Deng, Bailin; Noh, Seung-Tak (The Eurographics Association, 2022)
  • Learning a Style Space for Interactive Line Drawing Synthesis from Animated 3D Models 

    Wang, Zeyu; Wang, Tuanfeng Y.; Dorsey, Julie (The Eurographics Association, 2022)
    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 ...