Browsing by Author "Taketomi, Takafumi"

Now showing items 1-5 of 5

    • BareSkinNet: De-makeup and De-lighting via 3D Face Reconstruction 

      Yang, Xingchao; Taketomi, Takafumi (The Eurographics Association and John Wiley & Sons Ltd., 2022)
      We propose BareSkinNet, a novel method that simultaneously removes makeup and lighting influences from the face image. Our method leverages a 3D morphable model and does not require a reference clean face image or a specified ...

    • Context-based Style Transfer of Tokenized Gestures 

      Kuriyama, Shigeru; Mukai, Tomohiko; Taketomi, Takafumi; Mukasa, Tomoyuki (The Eurographics Association and John Wiley & Sons Ltd., 2022)
      Gestural animations in the amusement or entertainment field often require rich expressions; however, it is still challenging to synthesize characteristic gestures automatically. Although style transfer based on a neural ...

    • Garment Model Extraction from Clothed Mannequin Scan 

      Gao, Qiqi; Taketomi, Takafumi (© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2023)
      Modelling garments with rich details require enormous time and expertise of artists. Recent works re‐construct garments through segmentation of clothed human scan. However, existing methods rely on certain human body ...

    • Makeup Extraction of 3D Representation via Illumination-Aware Image Decomposition 

      Yang, Xingchao; Taketomi, Takafumi; Kanamori, Yoshihiro (The Eurographics Association and John Wiley & Sons Ltd., 2023)
      Facial makeup enriches the beauty of not only real humans but also virtual characters; therefore, makeup for 3D facial models is highly in demand in productions. However, painting directly on 3D faces and capturing real-world ...

    • Refinement of Hair Geometry by Strand Integration 

      Maeda, Ryota; Takayama, Kenshi; Taketomi, Takafumi (The Eurographics Association and John Wiley & Sons Ltd., 2023)
      Reconstructing 3D hair is challenging due to its complex micro-scale geometry, and is of essential importance for the efficient creation of high-fidelity virtual humans. Existing hair capture methods based on multi-view ...