Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00024
Moeko Ishii, T. Itoh
Hairstyle is an essential factor for representing individuals. It is in demand for ordinary persons who are not experts of professional software on three-dimensional computer graphics (3DCG) to represent hairstyles with flexible hairstyle modeling using 3DCG. We propose a method to realize sketch-based hairstyle modeling efficiently by supporting a viewpoint recommendation technique so that such users can easily perform hairstyle modeling. This method automatically finds appropriate viewpoints by evaluating the shapes of sketches on the projected 2D space. We aim to make this task of sketch-based hairstyle modeling efficient and straightforward because the technique avoids to manually control the viewpoint and prompts users to perform hair modeling intuitively. This paper introduces examples of viewpoint recommendation for two different input sketches.
{"title":"Viewpoint Selection for Sketch-based Hairstyle Modeling","authors":"Moeko Ishii, T. Itoh","doi":"10.1109/NicoInt50878.2020.00024","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00024","url":null,"abstract":"Hairstyle is an essential factor for representing individuals. It is in demand for ordinary persons who are not experts of professional software on three-dimensional computer graphics (3DCG) to represent hairstyles with flexible hairstyle modeling using 3DCG. We propose a method to realize sketch-based hairstyle modeling efficiently by supporting a viewpoint recommendation technique so that such users can easily perform hairstyle modeling. This method automatically finds appropriate viewpoints by evaluating the shapes of sketches on the projected 2D space. We aim to make this task of sketch-based hairstyle modeling efficient and straightforward because the technique avoids to manually control the viewpoint and prompts users to perform hair modeling intuitively. This paper introduces examples of viewpoint recommendation for two different input sketches.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123800008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00027
Yuji Sasaki, Taku Yamane, Masanori Fukui
This paper describes the virtual instrument "Musicurves" that plays sounds based on curves drawn on a blank score. The concept was to create a program that allows beginners to engage in both performing and composing music at the same time, by allowing the users to play sounds just by visually drawing their image of a melody as a line.
{"title":"Development of a Score-Based Virtual Instrument for Beginners, That Combines Composition With Performance","authors":"Yuji Sasaki, Taku Yamane, Masanori Fukui","doi":"10.1109/NicoInt50878.2020.00027","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00027","url":null,"abstract":"This paper describes the virtual instrument \"Musicurves\" that plays sounds based on curves drawn on a blank score. The concept was to create a program that allows beginners to engage in both performing and composing music at the same time, by allowing the users to play sounds just by visually drawing their image of a melody as a line.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"21 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132610451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00023
Jasmine Wu, Chia-Chen Kuo, Shao-Ting Hsiao, Kuo-Hsiang Chang, Shu-Hsin Liu
The virtual desktop infrastructure (VDI) service for the render farm platform at National Center for High-performance Computing (NCHC) was built to provide users with remote access to the render farm. Users from the film industry can utilize this platform throughout production, giving them the benefit of working on any regular laptop but with a dedicated Graphics Processing Unit (GPU). This paper describes an attempt at using NCHC’s VDI service for Augmented Reality (AR) and Virtual Reality (VR) to avoid the expensive equipment required.
{"title":"A Cloud Experiment for Virtual Reality and Augmented Reality in NCHC Render Farm","authors":"Jasmine Wu, Chia-Chen Kuo, Shao-Ting Hsiao, Kuo-Hsiang Chang, Shu-Hsin Liu","doi":"10.1109/NicoInt50878.2020.00023","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00023","url":null,"abstract":"The virtual desktop infrastructure (VDI) service for the render farm platform at National Center for High-performance Computing (NCHC) was built to provide users with remote access to the render farm. Users from the film industry can utilize this platform throughout production, giving them the benefit of working on any regular laptop but with a dedicated Graphics Processing Unit (GPU). This paper describes an attempt at using NCHC’s VDI service for Augmented Reality (AR) and Virtual Reality (VR) to avoid the expensive equipment required.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114808943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00022
T. Itoh, Ayana Murakami
Quality of training datasets is essential for the quality of machine learning. Machine learning projects often invite multiple workers for these annotation tasks for training dataset creation. It is important to observe on what types of contents multiple workers make different annotations, or which workers often make abnormal annotations, to guarantee the quality of training datasets. This paper presents a tool for the visualization of abnormality of annotations by multiple workers. The tool generates a matrix of abnormality of annotations for each of the images by each of the workers and displays as a heatmap. This paper introduces an example using a training dataset where estimated ages are annotated to 7,748 pictures of human faces by eight workers.
{"title":"Visualization of Individual Variation of Multiple Annotators Working on Training Datasets for Machine Learning","authors":"T. Itoh, Ayana Murakami","doi":"10.1109/NicoInt50878.2020.00022","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00022","url":null,"abstract":"Quality of training datasets is essential for the quality of machine learning. Machine learning projects often invite multiple workers for these annotation tasks for training dataset creation. It is important to observe on what types of contents multiple workers make different annotations, or which workers often make abnormal annotations, to guarantee the quality of training datasets. This paper presents a tool for the visualization of abnormality of annotations by multiple workers. The tool generates a matrix of abnormality of annotations for each of the images by each of the workers and displays as a heatmap. This paper introduces an example using a training dataset where estimated ages are annotated to 7,748 pictures of human faces by eight workers.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129166691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00032
Zhengyu Huang, Haoran Xie, K. Miyata
It is a challenge issue to recognize and comprehend hand drawn sketches for various applications such as image retrieval and image-based modeling. In this work, we propose an unsupervised learning framework to obtain the manifold of hand drawn sketches. We use DCT (Discrete Cosine Transform) to exact the feature of preprocessed sketch images from Quick Draw Dataset and adopt LLP (Locality Preserving Projections) to calculate the 2-D manifold of these sketches. Experiment result in flower sketches demonstrates the proposed approach is suitable to represent the manifold of hand drawn sketch.
{"title":"Manifold Learning for Hand Drawn Sketches","authors":"Zhengyu Huang, Haoran Xie, K. Miyata","doi":"10.1109/NicoInt50878.2020.00032","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00032","url":null,"abstract":"It is a challenge issue to recognize and comprehend hand drawn sketches for various applications such as image retrieval and image-based modeling. In this work, we propose an unsupervised learning framework to obtain the manifold of hand drawn sketches. We use DCT (Discrete Cosine Transform) to exact the feature of preprocessed sketch images from Quick Draw Dataset and adopt LLP (Locality Preserving Projections) to calculate the 2-D manifold of these sketches. Experiment result in flower sketches demonstrates the proposed approach is suitable to represent the manifold of hand drawn sketch.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114147118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00026
Bixuan Chen, Toshihiro Komma
This research is to present a method for real human face stylized modeling. It can transform the 3D data of an actual face into a model with an anime style, which could be applied to virtual character production in CG. Moreover, the "stylization" here is limited: We would pick a few famous Japanese anime and utilize their characters’ features to recreate a new face. The anime should be in natural styles that representatively depicted the faces of most Japanese, for example, the works of Kyoto Anime. As the image shows (Figure 1), our work focuses on how to transform the 3D facial data, specifically including three steps: 1. facial feature analyzation, 2. transforming relationship, and 3. modeling. We expect this system to complete automatic modeling in one hour to provide preliminary models to CG character makers for further manual improvement. Therefore, they do not need to spend more time in modeling from nothing but would be able to carry out artistic creation faster.
{"title":"Face Stylized Modeling for Virtual Character","authors":"Bixuan Chen, Toshihiro Komma","doi":"10.1109/NicoInt50878.2020.00026","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00026","url":null,"abstract":"This research is to present a method for real human face stylized modeling. It can transform the 3D data of an actual face into a model with an anime style, which could be applied to virtual character production in CG. Moreover, the \"stylization\" here is limited: We would pick a few famous Japanese anime and utilize their characters’ features to recreate a new face. The anime should be in natural styles that representatively depicted the faces of most Japanese, for example, the works of Kyoto Anime. As the image shows (Figure 1), our work focuses on how to transform the 3D facial data, specifically including three steps: 1. facial feature analyzation, 2. transforming relationship, and 3. modeling. We expect this system to complete automatic modeling in one hour to provide preliminary models to CG character makers for further manual improvement. Therefore, they do not need to spend more time in modeling from nothing but would be able to carry out artistic creation faster.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131921834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is a challenging task for common users to design and arrange the chain reaction with domino blocks. In this paper, we propose, Sketch2Domino, an interactive chain reaction design and guidance system with the input of the user freeform sketches. The proposed design system converts the captured user sketch into an arrangement graph of domino blocks. Then, the system formats the graph into a valid chain reaction and provides visual guidance with interactive projection mapping. The guidance system notices the user of the differences among the current blocks and the calculated results. This system can support multi-users to complete the chain-reaction design in group collaboration. It is verified that Sketch2Domino is convenient and helpful from our case studies.
{"title":"Sketch2Domino: Interactive Chain Reaction Design and Guidance","authors":"Yichen Peng, Yuki Mishima, Yamato Igarashi, Ryoma Miyauchi, Masahiro Okawa, Haoran Xie, K. Miyata","doi":"10.1109/NicoInt50878.2020.00013","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00013","url":null,"abstract":"It is a challenging task for common users to design and arrange the chain reaction with domino blocks. In this paper, we propose, Sketch2Domino, an interactive chain reaction design and guidance system with the input of the user freeform sketches. The proposed design system converts the captured user sketch into an arrangement graph of domino blocks. Then, the system formats the graph into a valid chain reaction and provides visual guidance with interactive projection mapping. The guidance system notices the user of the differences among the current blocks and the calculated results. This system can support multi-users to complete the chain-reaction design in group collaboration. It is verified that Sketch2Domino is convenient and helpful from our case studies.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131987052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/NicoInt50878.2020.00008
Shurentsetseg Erdenebayar, Keita Murakami, Fumito Chiba, K. Konno
Point-cloud-based techniques play a very significant role in the archaeological application for stone tools. Measured point data involve small noises, which are overlaps obtained through measurement by laser devices. Such noisy data make it difficult to extract highly accurate segmented flakes, which will be used for the refitted flake matching process, because potential feature points lying on the boundary edges are hardly extracted. To overcome this issue, this paper describes a method of recognizing flake surfaces with noisy point clouds. First, the resampling method is applied to remove the noise in the input data. Then, the surface variation is calculated with a various number of neighbors and the potential feature points are detected by analyzing its surface variation. After that, feature lines are extracted from the potential feature points. The feature lines represent boundary edges of the flake surfaces. Finally, flake surfaces are extracted by the feature-line-based segmentation method. The implementation of this work can recognize flake surfaces from noisy data.
{"title":"A Method of Recognizing Flake Surfaces from Noisy Point Cloud for Measuring Stone Tools","authors":"Shurentsetseg Erdenebayar, Keita Murakami, Fumito Chiba, K. Konno","doi":"10.1109/NicoInt50878.2020.00008","DOIUrl":"https://doi.org/10.1109/NicoInt50878.2020.00008","url":null,"abstract":"Point-cloud-based techniques play a very significant role in the archaeological application for stone tools. Measured point data involve small noises, which are overlaps obtained through measurement by laser devices. Such noisy data make it difficult to extract highly accurate segmented flakes, which will be used for the refitted flake matching process, because potential feature points lying on the boundary edges are hardly extracted. To overcome this issue, this paper describes a method of recognizing flake surfaces with noisy point clouds. First, the resampling method is applied to remove the noise in the input data. Then, the surface variation is calculated with a various number of neighbors and the potential feature points are detected by analyzing its surface variation. After that, feature lines are extracted from the potential feature points. The feature lines represent boundary edges of the flake surfaces. Finally, flake surfaces are extracted by the feature-line-based segmentation method. The implementation of this work can recognize flake surfaces from noisy data.","PeriodicalId":230190,"journal":{"name":"2020 Nicograph International (NicoInt)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131637118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：