Limited animation is one of the traditional techniques for producing cartoon animations. Owing to its expressive style, it has been enjoyed around the world. However, producing high quality animations using this limited style is time-consuming and...
24th ACM Symposium on Virtual Reality Software and Technology (VRST2018), 24(1166) 119 Nov 2018 [Refereed]
Due to the need to interact with virtual objects, the hand-object interaction has become an important element in mixed reality (MR) applications. In this paper, we propose a novel approach to handle the occlusion of augmented 3D object manipulatio...
Proceedings of the 11th International Conference on Machine Vision (ICMV 2018) V101 Nov 2018 [Refereed]
Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to this situa...
Proceedings of Pacific Graphics 2018 Oct 2018 [Refereed]
This paper proposes efficient path sampling for re-rendering scenes after material editing. The proposed sampling is based on Metropolis light transport (MLT) and dedicates path samples more to pixels receiving greater changes by editing. To rough...
How Do Computers See Makeup?: Investigating the Effects of Makeup on 3D Facial Reconstruction
Kanami Yamagishi, Takuya Kato, Ayano Kaneda and Shigeo Morishima
5th Women in Computer Vision Workshop in ECCV 2018 5 Sep 2018 [Refereed]
Makeup is a way to change one’s appearance. Previous studies on facial recognition show makeup’s potential to obfuscate one’s identity or to impersonate the identity of others. It is reasonable to assume that makeup would also affect 3D facial rec...
The research of face is one of the most active topics in computer vision, and deep neural networks (DNNs) fill the gap between human-level and computer-driven performance in face verification. The performance gap seems to get close in the accuracy...
Shugo Yamaguchi, Shunsuke Saito, Koki Nagano, Yajie Zhao, Weikai Chen, Kyle Olszewski, Shigeo Morishima, Hao Li
ACM Transactions on Graphics (TOG) 37(4) 162-1-162-14 Aug 2018 [Refereed]
We present a deep learning-based technique to infer high-quality facial reflectance and geometry given a single unconstrained image of the subject, which may contain partial occlusions and arbitrary illumination conditions. The reconstructed high-...
This poster proposes a new deep generative model that we refer to as region separative generative adversarial network (RSGAN), which can achieve face swapping between arbitrary image pairs and can robustly perform the swapping compared to previous...
How makeup experience changes how we see cosmetics?
CVPR Women in Computer Vision Workshop 2018 4 1884-1886 Jun 2018 [Refereed]
In recent years, a large number of makeup images have been shared on social media. Most of these images lack information about the cosmetics used, such as color, glitter or etc., while they are difficult to infer due to the diversity of skin color...
Proceedings of ACM International Conference on Multimedia Retrieval (ICMR2018) Jun 2018 [Refereed]
This paper presents an interactive face retrieval framework for clarifying an image representation envisioned by a user. Our system is designed for a situation in which the user wishes to find a person but has only visual memory of the person. We ...
Shoki Miyagawa, Yuki Koyama, Jun Kato, Masataka Goto, Shigeo Morishima
Proceedings of the ACM Symposium on Designing Interactive Systems (DIS2018) 39-43 Jun 2018 [Refereed]
We investigate the potential of music appreciation using spatial mapping techniques, which allow us to “place” audio sources in various locations within a physical space. We consider possible ways of this new appreciation style and list some desig...
In this paper, we present an integrated system for automatically generating and editing face images through face swapping, attribute-based editing, and random face parts synthesis. The proposed system is based on a deep neural network that variati...
Seita Kayukawa, Keita Higuchi, Ryo Yonetani, Masanori Nakamura, Yoichi Sato and Shigeo Morishima
Proceedings of 2018 CHI Conference on Human Factors in Computing Systems (CHI '18) Apr 2018 [Refereed]
This work presents the Dynamic Object Scanning (DO- Scanning), a novel interface that helps users browse long and untrimmed first-person videos quickly. The proposed interface offers users a small set of object cues generated automatically tailore...
Journal of Information Processing 59(3) 276-284 Mar 2018 [Refereed]
This paper presents a topic modeling method to retrieve similar music fragments and its application, Music-Mixer, which is a computer-aided DJ system that supports DJ performance by automatically mixing songs in a seamless manner. MusicMixer mixes...
Companion Publication of the 19th International ACM SIGACCESS Conference on Computers and Accessibility, DIS 2018, Hong Kong, China, June 09-13, 2018 39-43 2018 [Refereed]
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2018, Vancouver, BC, Canada, August 12-16, 2018, Posters Proceedings 69:1-69:2 2018 [Refereed]
Pavel A. Savkin,Tsukasa Fukusato,Takuya Kato,Shigeo Morishima
Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP, Funchal, Madeira, Portugal, January 27-29, 2018. 549-557 2018 [Refereed]
Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology, VRST 2018, Tokyo, Japan, November 28 - December 01, 2018 119:1-119:2 2018 [Refereed]
14TH INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTER ENTERTAINMENT TECHNOLOGY (ACE 2017) 10714 153-171 Dec 2017 [Refereed]
Limited animation is one of the traditional techniques for producing cartoon animations. Owing to its expressive style, it has been enjoyed around the world. However, producing high quality animations using this limited style is time-consuming and...
DanceDJ: A 3D Dance Animation Authoring System for Live Performance
14TH INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTER ENTERTAINMENT TECHNOLOGY (ACE 2017) 10714 653-670 Dec 2017 [Refereed]
Dance is an important component of live performance for expressing emotion and presenting visual context. Human dance performances typically require expert knowledge of dance choreography and professional rehearsal, which are too costly for casual...
Pavel A. Savkin, Shunke Saito, Jarich Vansteenberge, Tsulasa Fukusato, Lochlainn Wilson, Shigeo Morishima
Proceedings of the 23rd ACM Symposium on Visual Reality Software and Technology (VRST '17) Nov 2017 [Refereed]
Accurately tracking a Head Mounted Display (HMD) with a 6 degree of freedom is essential to achieve a confortable and a nausea free experience in Virtual Reality. Existing commercial HMD systems using synchronized Infrared (IR) camera and blinking...
The Institute of Image Electronics Engineers of Japan 46(4) 533-546 Oct 2017 [Refereed]
To synthesize photo-realistic images, simulating the subsurface scattering is highly important. However, physically accurate simulation of the subsurface scattering requires computationally complex integration over various optical paths going thro...
The 20th International Conference on Digital Audio Effects (DAFX2017) 32-39 Sep 2017 [Refereed]
Synthesizing a friction sound of deformable objects by a computer is challenging. We propose a novel physics-based approach to synthesize friction sounds based on dynamics simulation. In this work, we calculate the elastic deformation of an object...
Beautifying Font: Effective Handwriting Template for Mastering Expression of Chinese Calligraphy
We propose a novel font called Beautifying Font to assist learning techniques in writing Chinese calligraphy. Chinese calligraphy has various expressions but they are hard to acquire for beginners. Beautifying Font visualizes the speed and pressur...
Resizing of 3D model is necessary for computer graphics animation and application such as games and movies. In general, when users deform a target model, they built on a bounding box or a closed polygon mesh (cage) to enclose a target model. Then,...
Computer Vision and Pattern Recognition Workshop 179-186 Jul 2017 [Refereed]
In this paper, we propose a rally-rank evaluation based on the court transition information for automatic volleyball video summarization considering the contents of the game. Our system generates a summary video that consists of only more importan...
We propose a rally-rank evaluation based on the court transition information for volleyball video summarization considering the contents of the game. Our method uses the court transition information instead of non-robust visual features such as th...
Shintaro Yamamoto, Pavel Savkin, Takuya Kato, Shoichi Furukawa, Shigeo Morishima
Computer Graphics International 2017 Jun 2017 [Refereed]
This paper proposes an age progression method for facial videos. Age is one of the main factors that changes the appearance of the face, due to the associated sagging, spots, and wrinkles. These aging features change in appearance depending on fac...
The 30th International Conference on Computer Animation and Social Agents(CASA 2017) May 2017 [Refereed]
Creating secondary motion of character animation including jiggling of fat is demanded in the computer animation. In general, secondary motion from the primary motion of the character are expressed based on shape matching approaches. However, the ...
The 30th International Conference on Computer Animation and Social Agents(CASA 2017) May 2017 [Refereed]
Dance animations of a three-dimensional (3D) character rendered with computer graphics (CG) have been created by using motion capture systems or 3DCG animation editing tools. Since these methods require skills and a large amount of work from the c...
14th Sound and Music Computing Conference (SMC-17) May 2017 [Refereed]
There is a demand for arranging music composed using multiple instruments for a solo piano because there are several pianists who wish to practice playing their favorite songs or music. Generally, the method used for piano arrangement entails redu...
Facial Fattening and Slimming Simulation based on Skull Structure
12th International Conference on Computer Vision Theory and Applications 102-109 Feb 2017 [Refereed]
This paper presents a subtitle placement method that reduces unnecessary eye movements. Methods that vary the position of subtitles have been discussed in a previous study. However, subtitles may overlap the region of interest (ROI). Therefore, we...
Advances in Computer Entertainment Technology - 14th International Conference, ACE 2017, London, UK, December 14-16, 2017, Proceedings 153-171 2017 [Refereed]
Advances in Computer Entertainment Technology - 14th International Conference, ACE 2017, London, UK, December 14-16, 2017, Proceedings 653-670 2017 [Refereed]
Conventional markers can’t handle a large deformation with self-occlusion, so we make the marker hierarchical so that they can be referred to in a global range, and this makes it possible to accurately reflect the distortion of self-occlusion to t...
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '17, Los Angeles, CA, USA, July 30 - August 03, 2017, Posters Proceedings. 1:1-1:2 2017 [Refereed]
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '17, Los Angeles, CA, USA, July 30 - August 03, 2017, Posters Proceedings. 3:1-3:2 2017 [Refereed]
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '17, Los Angeles, CA, USA, July 30 - August 03, 2017, Posters Proceedings. 74:1-74:2 2017 [Refereed]
Pavel A. Savkin,Shunsuke Saito,Jarich Vansteenberge,Tsukasa Fukusato,Lochlainn Wilson,Shigeo Morishima
Proceedings of the 23rd ACM Symposium on Virtual Reality Software and Technology, VRST 2017, Gothenburg, Sweden, November 8-10, 2017 7:1-7:9 2017 [Refereed]
ACM SIGGRAPH ASIA 2016 Technical Brief Dec 2016 [Refereed]
We have a desire to edit images for various purposes such as art, entertainment, and film production so texture synthesis methods have been proposed. Especially, PatchMatch algorithm [Barnes et al.2009] enabled us to easily use many image editing ...
An appearance of a human face changes with aging: sagging, spots, somberness, and wrinkles would be observed. Considering these changes, aging simulation techniques that estimate an aged facial image is required for a long-term criminal or missing...
Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 2: IVAPP, Rome, Italy, February 27-29, 2016. 249-256 2016 [Refereed]
Shoichi Furukawa,Takuya Kato,Pavel A. Savkin,Shigeo Morishima
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '16, Anaheim, CA, USA, July 24-28, 2016, Posters Proceedings 19:1-19:2 2016 [Refereed]
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '16, Anaheim, CA, USA, July 24-28, 2016, Posters Proceedings 23:1-23:2 2016 [Refereed]
Tsukasa Nozawa,Takuya Kato,Pavel A. Savkin,Naoki Nozawa,Shigeo Morishima
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '16, Anaheim, CA, USA, July 24-28, 2016, Posters Proceedings 24:1-24:2 2016 [Refereed]
Proceedings of the ACM International Conference on Interactive Experiences for TV and Online Video, TVX 2016, Chicago, Illinois, USA, June 22-24, 2016 123-128 2016 [Refereed]
Computer Graphics Forum (CGF) 34(7) Oct 2015 [Refereed]
Due to the recent advancement of computer graphics hardware and software algorithms, deformable characters have become more and more popular in real‐time applications such as computer games. While there are mature techniques to generate primary de...
Automatic Generation of Photorealistic 3D Inner Mouth Animation only from Frontal Images
Proceedings of the 12th International Conference on Advances in Computer Entertainment Technology, ACE 2015, Iskandar, Malaysia, November 16-19, 2015 41:1-41:5 2015 [Refereed]
11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2015, Ljubljana, Slovenia, May 4-8, 2015 1-6 2015 [Refereed]
GRAPP 2015 - Proceedings of the 10th International Conference on Computer Graphics Theory and Applications, Berlin, Germany, 11-14 March, 2015. 332-339 2015 [Refereed]
Advances in Visual Computing - 11th International Symposium, ISVC 2015, Las Vegas, NV, USA, December 14-16, 2015, Proceedings, Part II 9475 137-149 2015 [Refereed]
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '15, Los Angeles, CA, USA, August 9-13, 2015, Posters Proceedings 42:1 2015 [Refereed]
Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH '15, Los Angeles, CA, USA, August 9-13, 2015, Posters Proceedings 44:1 2015 [Refereed]
We introduce a new silhouette-based representation for modeling clothed human
bodies using deep generative models. Our method can reconstruct a complete and
textured 3D model of a person wearing clothes from a single input picture.
Inspired by the...
This paper presents FSNet, a deep generative model for image-based face
swapping. Traditionally, face-swapping methods are based on three-dimensional
morphable models (3DMMs), and facial textures are replaced between the
estimated three-dimensiona...
SIGGRAPH Asia 2017 Technical Briefs, SA 2017 Nov 2017
' 2017 ACM. In this paper, we present an interactive framework to model garments for animals from a template garment model based on correspondences between the source and the target bodies. We address two critical challenges of garment transfer ac...
VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 6 102-109 Jan 2017
DAFx 2017 - Proceedings of the 20th International Conference on Digital Audio Effects 32-39 Jan 2017
Synthesizing a friction sound of deformable objects by a computer is challenging. We propose a novel physics-based approach to synthesize friction sounds based on dynamics simulation. In this work, we calculate the elastic deformation of an object...
waseda.jp