A reconstruction of a human face shape from a single image is an important theme for criminal investigation such as recognition of suspected people from surveillance cameras with only a few frames. It is, however, still difficult to recover a face shape from a non-frontal face image. Method using shading cues on a face depends on the lighting circumstance and cannot be adapted to images in which shadows occurs, for example [Kemelmacher et al. 2011]. On the other hand, [Blanz et al. 2004] reconstructed a shape by 3D Morphable Model (3DMM) only with facial feature points. This method, however, requires the pose-wise correspondences of vertices in the model to feature points of input image because a face contour cannot be seen when the facial direction is not the front. In this paper, we propose a method which can reconstruct a facial shape from a non-frontal face image only with a single general correspondence table. Our method searches for the correspondences of points on a facial contour in the iterative reconstruction process, and makes the reconstruction simple and stable.
从单个图像中重建人脸形状是刑事调查的一个重要主题，例如从只有几帧的监控摄像机中识别嫌疑人。然而，从非正面脸图像中恢复脸型仍然很困难。在人脸上使用阴影线索的方法取决于光照环境，不能适用于出现阴影的图像，例如[Kemelmacher et al. 2011]。另一方面[Blanz et al. 2004]仅使用面部特征点通过3D变形模型(3D Morphable Model, 3DMM)重建形状。然而，该方法需要模型中顶点与输入图像特征点的位姿对应，因为当面部方向不是正面时，无法看到面部轮廓。本文提出了一种仅使用单个通用对应表就能从非正面人脸图像中重建人脸形状的方法。该方法在迭代重建过程中搜索面部轮廓上点的对应关系，使重建过程简单稳定。
{"title":"3D face reconstruction from a single non-frontal face image","authors":"N. Nozawa, Daiki Kuwahara, S. Morishima","doi":"10.1145/2787626.2792634","DOIUrl":"https://doi.org/10.1145/2787626.2792634","url":null,"abstract":"A reconstruction of a human face shape from a single image is an important theme for criminal investigation such as recognition of suspected people from surveillance cameras with only a few frames. It is, however, still difficult to recover a face shape from a non-frontal face image. Method using shading cues on a face depends on the lighting circumstance and cannot be adapted to images in which shadows occurs, for example [Kemelmacher et al. 2011]. On the other hand, [Blanz et al. 2004] reconstructed a shape by 3D Morphable Model (3DMM) only with facial feature points. This method, however, requires the pose-wise correspondences of vertices in the model to feature points of input image because a face contour cannot be seen when the facial direction is not the front. In this paper, we propose a method which can reconstruct a facial shape from a non-frontal face image only with a single general correspondence table. Our method searches for the correspondences of points on a facial contour in the iterative reconstruction process, and makes the reconstruction simple and stable.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117311085","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}
[Hong et al. 2008] proposed a hybrid method of Eulerian grids and Lagrangian particles to represent small-scale bubbles in large-scale water. In the simulation, bubbles rise freely in the water; however, bubble seeds are set at random at the bottom and they disappear as soon as they arrive at the water surface. [Patkar et al. 2013] also proposed a hybrid Lagrangian-Eulerian framework to visualize both small and large scale bubbles. A bubble that exits the spout of a water dispenser flows up in the water with changing its shape; however, they did not simulate the rupture process of bubble. Then, [Mukai et al. 2012] tried a rupture simulation by using MPS method; however, it did not consider the high density ratio of the water to the air so that the bubble ruptured gradually. Therefore, this paper proposes a method of bubble rupture simulation, where a wave is generated after a bubble has ruptured rapidly, by considering the high density ratio of the water to the air.
[Hong et al. 2008]提出了一种欧拉网格和拉格朗日粒子的混合方法来表示大尺度水中的小尺度气泡。在模拟中，气泡在水中自由上升;然而，气泡种子是在底部随机设置的，它们一到达水面就消失了。[Patkar et al. 2013]还提出了一种混合拉格朗日-欧拉框架来可视化小尺度和大尺度气泡。饮水机壶口的气泡会随着形状的改变而向上流动;然而，他们没有模拟气泡的破裂过程。随后，[Mukai et . 2012]尝试使用MPS方法进行破裂模拟;然而，它没有考虑到水与空气的高密度比，使气泡逐渐破裂。因此，本文提出了一种气泡破裂模拟方法，即考虑到水与空气的高密度比，在气泡迅速破裂后产生波浪。
{"title":"Bubble rupture simulation by considering high density ratio","authors":"N. Mukai, Naoki Mita, Youngha Chang","doi":"10.1145/2787626.2787642","DOIUrl":"https://doi.org/10.1145/2787626.2787642","url":null,"abstract":"[Hong et al. 2008] proposed a hybrid method of Eulerian grids and Lagrangian particles to represent small-scale bubbles in large-scale water. In the simulation, bubbles rise freely in the water; however, bubble seeds are set at random at the bottom and they disappear as soon as they arrive at the water surface. [Patkar et al. 2013] also proposed a hybrid Lagrangian-Eulerian framework to visualize both small and large scale bubbles. A bubble that exits the spout of a water dispenser flows up in the water with changing its shape; however, they did not simulate the rupture process of bubble. Then, [Mukai et al. 2012] tried a rupture simulation by using MPS method; however, it did not consider the high density ratio of the water to the air so that the bubble ruptured gradually. Therefore, this paper proposes a method of bubble rupture simulation, where a wave is generated after a bubble has ruptured rapidly, by considering the high density ratio of the water to the air.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122050076","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}
Xiang 'Anthony' Chen, Stelian Coros, Jennifer Mankoff, S. Hudson
One powerful aspect of 3D printing is its ability to extend, repair, or more generally modify everyday objects. However, nearly all existing work implicitly assumes that whole objects are to be printed from scratch. Designing objects as extensions or enhancements of existing ones is a laborious process in most of today's 3D authoring tools. This paper presents a framework for 3D printing to augment existing objects that covers a wide range of attachment options. We illustrate the framework through three exemplar attachment techniques - print-over, print-to-affix, and print-through. We implemented these techniques in Encore, a design tool that supports a range of analysis with visualization for users to explore design options and tradeoffs among these metrics. Encore also generates 3D models for production, addressing issues such as support jigs and contact geometry between the attached part and the original object.
{"title":"Encore: 3D printed augmentation of everyday objects with printed-over, affixed and interlocked attachments","authors":"Xiang 'Anthony' Chen, Stelian Coros, Jennifer Mankoff, S. Hudson","doi":"10.1145/2787626.2787650","DOIUrl":"https://doi.org/10.1145/2787626.2787650","url":null,"abstract":"One powerful aspect of 3D printing is its ability to extend, repair, or more generally modify everyday objects. However, nearly all existing work implicitly assumes that whole objects are to be printed from scratch. Designing objects as extensions or enhancements of existing ones is a laborious process in most of today's 3D authoring tools. This paper presents a framework for 3D printing to augment existing objects that covers a wide range of attachment options. We illustrate the framework through three exemplar attachment techniques - print-over, print-to-affix, and print-through. We implemented these techniques in Encore, a design tool that supports a range of analysis with visualization for users to explore design options and tradeoffs among these metrics. Encore also generates 3D models for production, addressing issues such as support jigs and contact geometry between the attached part and the original object.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121231927","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}
Point-Based Global Illumination (PBGI) [2008] is a popular rendering method in special effects and motion picture productions. This algorithm provides a diffuse global illumination solution by caching radiance in a mesh-less hierarchical data structure during a pre-process, while solving for visibility over this cache, at rendering time and for each receiver, using microbuffers, which are localized depth and color buffer inspired from real time rendering environments. As a result, noise free ambient occlusion, indirect soft shadows and color bleeding effects are computed efficiently for high resolution image output and in a temporally coherent fashion. We propose an evolution of this method to address the case of non-diffuse inter-reflections and refractions using wavelets instead of spherical harmonics (see Fig. 1). We also propose a new importance-driven adaptive microbuffer model to capture accurately incoming radiance at a point. Furthermore, we evaluate outgoing radiance using a fast wavelet radiance product, containing the memory footprint by encoding hierarchically the wavelets tree.
基于点的全局照明(Point-Based Global Illumination, PBGI)[2008]是一种在特效和电影制作中非常流行的渲染方法。该算法通过在预处理期间在无网格分层数据结构中缓存亮度来提供漫射全局照明解决方案，同时在渲染时和每个接收器上解决该缓存的可见性，使用微缓冲区，微缓冲区是受实时渲染环境启发的局部深度和颜色缓冲区。因此，无噪声环境遮挡，间接软阴影和颜色出血效果被有效地计算为高分辨率图像输出和在时间上一致的方式。我们提出了对该方法的改进，以解决使用小波代替球面谐波的非漫反射和折射情况(见图1)。我们还提出了一种新的重要性驱动的自适应微缓冲模型，以准确捕获某一点的入射辐射。此外，我们使用快速小波辐射积来评估外向辐射，通过分层编码小波树来包含内存占用。
{"title":"Non-diffuse effects for point-based global illumination","authors":"Beibei Wang, Xiangxu Meng, T. Boubekeur","doi":"10.1145/2787626.2787662","DOIUrl":"https://doi.org/10.1145/2787626.2787662","url":null,"abstract":"Point-Based Global Illumination (PBGI) [2008] is a popular rendering method in special effects and motion picture productions. This algorithm provides a diffuse global illumination solution by caching radiance in a mesh-less hierarchical data structure during a pre-process, while solving for visibility over this cache, at rendering time and for each receiver, using microbuffers, which are localized depth and color buffer inspired from real time rendering environments. As a result, noise free ambient occlusion, indirect soft shadows and color bleeding effects are computed efficiently for high resolution image output and in a temporally coherent fashion. We propose an evolution of this method to address the case of non-diffuse inter-reflections and refractions using wavelets instead of spherical harmonics (see Fig. 1). We also propose a new importance-driven adaptive microbuffer model to capture accurately incoming radiance at a point. Furthermore, we evaluate outgoing radiance using a fast wavelet radiance product, containing the memory footprint by encoding hierarchically the wavelets tree.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125892143","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}
Daria Tsoupikova, S. Rettberg, Roderick Coover, Arthur Nishimoto
We describe the first virtual reality art performance Hearts and Minds: The Interrogations Project developed using a novel method for direct output of the Unity-based virtual reality projects into CAVE2™ [Febretti et al. 2013] environment. This work incorporates original research, technological innovation and creative arts in an adaptation of veterans' testimonies detailing US military interrogations and abuses of prisoners in Iraq during the American counter-insurgency campaign in the early 2000s. It presents a debate focusing on interrogation methods, torture and its consequences, and Post Traumatic Stress Disorder experienced by solders who have participated in such acts. This work was developed at the Electronic Visualization Lab in Chicago through a unique international collaboration between artists, scientists, and researchers from five different Universities. The methods developed for this project allow hands-on education of virtual reality by letting students create their own virtual environments and exhibit them in the CAVE2 quickly.
{"title":"The battle for hearts and minds: interrogation and torture in the age of war","authors":"Daria Tsoupikova, S. Rettberg, Roderick Coover, Arthur Nishimoto","doi":"10.1145/2787626.2787633","DOIUrl":"https://doi.org/10.1145/2787626.2787633","url":null,"abstract":"We describe the first virtual reality art performance Hearts and Minds: The Interrogations Project developed using a novel method for direct output of the Unity-based virtual reality projects into CAVE2™ [Febretti et al. 2013] environment. This work incorporates original research, technological innovation and creative arts in an adaptation of veterans' testimonies detailing US military interrogations and abuses of prisoners in Iraq during the American counter-insurgency campaign in the early 2000s. It presents a debate focusing on interrogation methods, torture and its consequences, and Post Traumatic Stress Disorder experienced by solders who have participated in such acts. This work was developed at the Electronic Visualization Lab in Chicago through a unique international collaboration between artists, scientists, and researchers from five different Universities. The methods developed for this project allow hands-on education of virtual reality by letting students create their own virtual environments and exhibit them in the CAVE2 quickly.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124264003","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}
K. Kanazawa, R. Tanabe, Tomoaki Moriya, Tokiichiro Takahashi
Realistic representation of nature scenes is one of the most challenging areas in computer graphics community. There are important factors to synthesize realistic scenes in 3D CG which are decayed materials such as dead trees, weathered statues, rusty metals and so on. We are interested in the methodology for simulating its decaying processes. In this paper, we propose a simple method for rust aging simulation based on a probabilistic cellular automaton model taking into account object's geometries.
{"title":"Rust aging simulation considering object's geometries","authors":"K. Kanazawa, R. Tanabe, Tomoaki Moriya, Tokiichiro Takahashi","doi":"10.1145/2787626.2792641","DOIUrl":"https://doi.org/10.1145/2787626.2792641","url":null,"abstract":"Realistic representation of nature scenes is one of the most challenging areas in computer graphics community. There are important factors to synthesize realistic scenes in 3D CG which are decayed materials such as dead trees, weathered statues, rusty metals and so on. We are interested in the methodology for simulating its decaying processes. In this paper, we propose a simple method for rust aging simulation based on a probabilistic cellular automaton model taking into account object's geometries.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133547187","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}
Hisataka Suzuki, Rex Hsieh, Ryotaro Tsuda, Akihiko Shirai
In recent years, 3D technology has become so widespread that the technology alone no longer fascinates the viewers. To achieve further technical innovations on display experience, we should explore the limitations of 3D devices.
{"title":"ExPixel FPGA: multiplex hidden imagery for HDMI video sources","authors":"Hisataka Suzuki, Rex Hsieh, Ryotaro Tsuda, Akihiko Shirai","doi":"10.1145/2787626.2787645","DOIUrl":"https://doi.org/10.1145/2787626.2787645","url":null,"abstract":"In recent years, 3D technology has become so widespread that the technology alone no longer fascinates the viewers. To achieve further technical innovations on display experience, we should explore the limitations of 3D devices.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116332811","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}
In this work, we have developed an approach to include global illumination effects into Chinese Paintings (see Figure 1). Our method provides a robust approach to represent tone and value in a way similar to how Chinese Ink-and-Brush is painted. The method, especially, supports reflection, shadow, atmospheric, depth and weathering effects. Using the method, we can recapture the aesthetic of irregularity in shapes and forms commonly seen in Chinese Painting. We also arrange composition in 3D to obtain multi-camera imagee that matches the compositions in Chinese painting. We also included cinematic lighting aesthetic in 3D Chinese painting to enhance mood and storytelling.
{"title":"Chinese ink and brush painting with reflections","authors":"Siran Liu, E. Akleman","doi":"10.1145/2787626.2792613","DOIUrl":"https://doi.org/10.1145/2787626.2792613","url":null,"abstract":"In this work, we have developed an approach to include global illumination effects into Chinese Paintings (see Figure 1). Our method provides a robust approach to represent tone and value in a way similar to how Chinese Ink-and-Brush is painted. The method, especially, supports reflection, shadow, atmospheric, depth and weathering effects. Using the method, we can recapture the aesthetic of irregularity in shapes and forms commonly seen in Chinese Painting. We also arrange composition in 3D to obtain multi-camera imagee that matches the compositions in Chinese painting. We also included cinematic lighting aesthetic in 3D Chinese painting to enhance mood and storytelling.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124550512","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}
Medial axis is a classical shape descriptor that is widely used in computer graphics, computer vision, and pattern recognition. Defined elegantly as the locus of points with multiple nearest neighbors on the object boundary, the medial axis preserves both the structure and topology of the object in a compact form - a geometry that has one lower dimension than the object itself.
{"title":"Burning the medial axis","authors":"E. Chambers","doi":"10.1145/2787626.2792658","DOIUrl":"https://doi.org/10.1145/2787626.2792658","url":null,"abstract":"Medial axis is a classical shape descriptor that is widely used in computer graphics, computer vision, and pattern recognition. Defined elegantly as the locus of points with multiple nearest neighbors on the object boundary, the medial axis preserves both the structure and topology of the object in a compact form - a geometry that has one lower dimension than the object itself.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114585922","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}
Seungbae Bang, Byungkuk Choi, Roger Blanco i Ribera, Meekyoung Kim, Sung-Hee Lee, Jun-yong Noh
Skeleton-driven animation is a widespread technique, which is frequently used in film and video game productions to animate 3D characters. The process of preparing characters for skeletal animation is referred to as character rigging. Commercial applications such as Maya or 3DS Max provide many tool that support this process, including the 'joint tool' and the 'paint skin weights tool'. Most of these tools are difficult to use for novice users. Even for professional artists, it requires many hours of intensive effort.
{"title":"Interactive rigging","authors":"Seungbae Bang, Byungkuk Choi, Roger Blanco i Ribera, Meekyoung Kim, Sung-Hee Lee, Jun-yong Noh","doi":"10.1145/2787626.2787659","DOIUrl":"https://doi.org/10.1145/2787626.2787659","url":null,"abstract":"Skeleton-driven animation is a widespread technique, which is frequently used in film and video game productions to animate 3D characters. The process of preparing characters for skeletal animation is referred to as character rigging. Commercial applications such as Maya or 3DS Max provide many tool that support this process, including the 'joint tool' and the 'paint skin weights tool'. Most of these tools are difficult to use for novice users. Even for professional artists, it requires many hours of intensive effort.","PeriodicalId":269034,"journal":{"name":"ACM SIGGRAPH 2015 Posters","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133232740","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：