We propose a direct-view see-through light field near-eye display (NED) using a semi-reflective embedded concave micromirror array (ECMMA) that can generate virtual images at different depths of focus. The ECMMA is a planar optical element having a thin, semi-reflective embedded metallic film for the mirror array. Being a flat element, the ECMMA has zero net refractive power, and the light rays originating from the background scene do not change their original direction of propagation when they pass the ECMMA. Therefore, the see-through view of the proposed ECMMA-NED looks clear with negligible disturbance to the quality of the background scene.
{"title":"Embedded Concave Micromirror Array-based See-through Light Field Near-eye Display","authors":"Hongbae S. Park, R. Hoskinson, B. Stoeber","doi":"10.1145/3355088.3365141","DOIUrl":"https://doi.org/10.1145/3355088.3365141","url":null,"abstract":"We propose a direct-view see-through light field near-eye display (NED) using a semi-reflective embedded concave micromirror array (ECMMA) that can generate virtual images at different depths of focus. The ECMMA is a planar optical element having a thin, semi-reflective embedded metallic film for the mirror array. Being a flat element, the ECMMA has zero net refractive power, and the light rays originating from the background scene do not change their original direction of propagation when they pass the ECMMA. Therefore, the see-through view of the proposed ECMMA-NED looks clear with negligible disturbance to the quality of the background scene.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116675415","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}
Ruotong Li, Tianpei Yang, Weixin Si, Xiangyun Liao, Qiong Wang, R. Klein, P. Heng
CT-guided radiofrequency ablation (RFA) has evolved rapidly over the past decade and become a widely accepted treatment option for patients with liver tumors. However, it is hard for doctors to locate tumors precisely while avoid damaging the surrounding risk structures with 2D CT images, which only provides limited static information, especially in case of respiratory motion. This paper presents a novel augmented reality guidance modality for improving the precision of liver tumors punctures by providing visual cue of 3D personalized anatomy with respiratory motion. Optical see-through display devices Epson MoveRio BT300 and Microsoft HoloLens are used to mix pre-operative 3D personalized data and intra-operative physical scene. Here an augmented reality based surgical navigation pipeline is proposed to achieve the transformation from raw medical data to virtual guidance information and precisely superimpose this information onto real experimental animal. In addition, to alleviate the difficulty during needle placement induced by respiratory motion, we proposed a correlation model to real-timely predict the tumor position via regression based respiration state estimation and the statistical tumor motion model. We experimentally validated the proposed system on in vivo beagle dogs with artificial lesion, which can effectively improve the puncture efficiency and precision. The proposed augmented reality modality is a general strategy to guide the doctors perform precise percutaneous puncture under respiration conditions and has the potential to be used for other surgical navigation tasks.
{"title":"Augmented Reality Guided Respiratory Liver Tumors Punctures: A Preliminary Feasibility Study","authors":"Ruotong Li, Tianpei Yang, Weixin Si, Xiangyun Liao, Qiong Wang, R. Klein, P. Heng","doi":"10.1145/3355088.3365166","DOIUrl":"https://doi.org/10.1145/3355088.3365166","url":null,"abstract":"CT-guided radiofrequency ablation (RFA) has evolved rapidly over the past decade and become a widely accepted treatment option for patients with liver tumors. However, it is hard for doctors to locate tumors precisely while avoid damaging the surrounding risk structures with 2D CT images, which only provides limited static information, especially in case of respiratory motion. This paper presents a novel augmented reality guidance modality for improving the precision of liver tumors punctures by providing visual cue of 3D personalized anatomy with respiratory motion. Optical see-through display devices Epson MoveRio BT300 and Microsoft HoloLens are used to mix pre-operative 3D personalized data and intra-operative physical scene. Here an augmented reality based surgical navigation pipeline is proposed to achieve the transformation from raw medical data to virtual guidance information and precisely superimpose this information onto real experimental animal. In addition, to alleviate the difficulty during needle placement induced by respiratory motion, we proposed a correlation model to real-timely predict the tumor position via regression based respiration state estimation and the statistical tumor motion model. We experimentally validated the proposed system on in vivo beagle dogs with artificial lesion, which can effectively improve the puncture efficiency and precision. The proposed augmented reality modality is a general strategy to guide the doctors perform precise percutaneous puncture under respiration conditions and has the potential to be used for other surgical navigation tasks.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"920 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116184239","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}
This paper presents a novel solution for approximations to some large convolution kernels by leveraging a weighted box-filtered image pyramid set. Convolution filters are widely used, but still compute-intensive for real-time rendering when the kernel size is large. Our algorithm approximates the convolution kernels, such as Gaussian and cosine filters, by two phases of down and up sampling on a GPU. The computational complexity only depends on the input image resolution and is independent of the kernel size. Therefore, our method can be applied to nonuniform blurs, irradiance probe generations, and ray-traced glossy global illuminations in real time, and runs in effective and efficient performance.
{"title":"The Power of Box Filters: Real-time Approximation to Large Convolution Kernel by Box-filtered Image Pyramid","authors":"Tianchen Xu, Xiaohua Ren, E. Wu","doi":"10.1145/3355088.3365143","DOIUrl":"https://doi.org/10.1145/3355088.3365143","url":null,"abstract":"This paper presents a novel solution for approximations to some large convolution kernels by leveraging a weighted box-filtered image pyramid set. Convolution filters are widely used, but still compute-intensive for real-time rendering when the kernel size is large. Our algorithm approximates the convolution kernels, such as Gaussian and cosine filters, by two phases of down and up sampling on a GPU. The computational complexity only depends on the input image resolution and is independent of the kernel size. Therefore, our method can be applied to nonuniform blurs, irradiance probe generations, and ray-traced glossy global illuminations in real time, and runs in effective and efficient performance.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128009991","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}
Gayoung Lee, Dohyun Kim, Y. Yoo, Dongyoon Han, Jung-Woo Ha, Jaehyuk Chang
Converting hand-drawn sketches into clean line drawings is a crucial step for diverse artistic works such as comics and product designs. Recent data-driven methods using deep learning have shown their great abilities to automatically simplify sketches on raster images. Since it is difficult to collect or generate paired sketch and line images, lack of training data is a main obstacle to use these models. In this paper, we propose a training scheme that requires only unpaired sketch and line images for learning sketch-to-line translation. To do this, we first generate realistic paired sketch and line images from unpaired sketch and line images using rule-based line augmentation and unsupervised texture conversion. Next, with our synthetic paired data, we train a model for sketch-to-line translation using supervised learning. Compared to unsupervised methods that use cycle consistency losses, our model shows better performance at removing noisy strokes. We also show that our model simplifies complicated sketches better than models trained on a limited number of handcrafted paired data.
{"title":"Unpaired Sketch-to-Line Translation via Synthesis of Sketches","authors":"Gayoung Lee, Dohyun Kim, Y. Yoo, Dongyoon Han, Jung-Woo Ha, Jaehyuk Chang","doi":"10.1145/3355088.3365163","DOIUrl":"https://doi.org/10.1145/3355088.3365163","url":null,"abstract":"Converting hand-drawn sketches into clean line drawings is a crucial step for diverse artistic works such as comics and product designs. Recent data-driven methods using deep learning have shown their great abilities to automatically simplify sketches on raster images. Since it is difficult to collect or generate paired sketch and line images, lack of training data is a main obstacle to use these models. In this paper, we propose a training scheme that requires only unpaired sketch and line images for learning sketch-to-line translation. To do this, we first generate realistic paired sketch and line images from unpaired sketch and line images using rule-based line augmentation and unsupervised texture conversion. Next, with our synthetic paired data, we train a model for sketch-to-line translation using supervised learning. Compared to unsupervised methods that use cycle consistency losses, our model shows better performance at removing noisy strokes. We also show that our model simplifies complicated sketches better than models trained on a limited number of handcrafted paired data.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"63 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123307329","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}
GANs make it effective to generate artworks using appropriate collections. However, most training dataset either contain paintings that were only from one artist or contain only one category. There is few training datasets for Chinese traditional figure paintings. This paper presents a new high-quality dataset named ChinaStyle Dataset including six categories, containing 1913 images totally. We further proposes Mask-Aware Generative Adversarial Networks (MA-GAN) to transfer realistic portraiture to different styles of Chinese paintings. Different from existing mothed, MA-GAN uses a single model only once with our unpaired dataset. Besides, Mask-aware strategy is used to generate free-hand style of Chinese paintings. In addition, a color preserved loss is proposed to alleviate the color free problem. Experimental results and user study demonstrate that MA-GAN achieves a natural and competitive performance compared with existing methods.
{"title":"ChinaStyle: A Mask-Aware Generative Adversarial Network for Chinese Traditional Image Translation","authors":"Yuan Wang, W. Zhang, Peng Chen","doi":"10.1145/3355088.3365148","DOIUrl":"https://doi.org/10.1145/3355088.3365148","url":null,"abstract":"GANs make it effective to generate artworks using appropriate collections. However, most training dataset either contain paintings that were only from one artist or contain only one category. There is few training datasets for Chinese traditional figure paintings. This paper presents a new high-quality dataset named ChinaStyle Dataset including six categories, containing 1913 images totally. We further proposes Mask-Aware Generative Adversarial Networks (MA-GAN) to transfer realistic portraiture to different styles of Chinese paintings. Different from existing mothed, MA-GAN uses a single model only once with our unpaired dataset. Besides, Mask-aware strategy is used to generate free-hand style of Chinese paintings. In addition, a color preserved loss is proposed to alleviate the color free problem. Experimental results and user study demonstrate that MA-GAN achieves a natural and competitive performance compared with existing methods.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130520368","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}
Pedro de Almeida Sacramento, R. Ferreira, M. Andrade
The usage of shape changing interfaces is widely discussed in the HCI field as a promising strategy for the physical representation of digital data. Such interfaces are expected to greatly impact a wide range of applications, such as virtual reality, architectural design and education of blind people. Unfortunately, the widespread usage of pin-based shape displays is currently limited by their typically high manufacturing costs. The high costs of pin-based shape displays are mainly due to the number of actuators, which tends to grow quadratically with display resolution. Given that, we present Bezalel: a solution for pin-based shape displays that allows 2 actuators to efficiently actuate pin-based shape displays with n pins. Our solution is able to fully render any 2.5D shape within a time proportional to , which outperforms the 2014 Lemelson-MIT ”Use it!” graduate winner solution using half as much actuators. Additionally, results also show that, for specific shapes, our approach can perform as well as the most efficient and much more expensive technologies currently used. We expect that our solution will make it possible to create low-cost actuated surfaces with different sizes, from small tactile objects to large structures such as shape-changing floors.
{"title":"Bezalel - Towards low-cost pin-based shape displays","authors":"Pedro de Almeida Sacramento, R. Ferreira, M. Andrade","doi":"10.1145/3355088.3365144","DOIUrl":"https://doi.org/10.1145/3355088.3365144","url":null,"abstract":"The usage of shape changing interfaces is widely discussed in the HCI field as a promising strategy for the physical representation of digital data. Such interfaces are expected to greatly impact a wide range of applications, such as virtual reality, architectural design and education of blind people. Unfortunately, the widespread usage of pin-based shape displays is currently limited by their typically high manufacturing costs. The high costs of pin-based shape displays are mainly due to the number of actuators, which tends to grow quadratically with display resolution. Given that, we present Bezalel: a solution for pin-based shape displays that allows 2 actuators to efficiently actuate pin-based shape displays with n pins. Our solution is able to fully render any 2.5D shape within a time proportional to , which outperforms the 2014 Lemelson-MIT ”Use it!” graduate winner solution using half as much actuators. Additionally, results also show that, for specific shapes, our approach can perform as well as the most efficient and much more expensive technologies currently used. We expect that our solution will make it possible to create low-cost actuated surfaces with different sizes, from small tactile objects to large structures such as shape-changing floors.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130602571","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}
Volume rendering has useful applications with emerging technologies such as virtual and augmented reality. The high frame rate targets of these technologies poses a problem for volume rendering because of its very high computational complexity compared with conventional surface rendering. We developed an efficient empty space skipping algorithm for accelerating volume rendering. A distance map is generated which indicates the Chebyshev distance to the nearest occupied region (with non-transparent voxels) within a volume. The distance map is used to efficiently skip empty regions while volume ray casting. We show improved performance over state-of-the-art empty space skipping techniques.
{"title":"Accelerated Volume Rendering with Chebyshev Distance Maps","authors":"Lachlan Deakin, M. Knackstedt","doi":"10.1145/3355088.3365164","DOIUrl":"https://doi.org/10.1145/3355088.3365164","url":null,"abstract":"Volume rendering has useful applications with emerging technologies such as virtual and augmented reality. The high frame rate targets of these technologies poses a problem for volume rendering because of its very high computational complexity compared with conventional surface rendering. We developed an efficient empty space skipping algorithm for accelerating volume rendering. A distance map is generated which indicates the Chebyshev distance to the nearest occupied region (with non-transparent voxels) within a volume. The distance map is used to efficiently skip empty regions while volume ray casting. We show improved performance over state-of-the-art empty space skipping techniques.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125336411","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}
N. Kuratomo, Kazuki Yamada, Soh Masuko, T. Yamanaka, K. Zempo
The purpose of this study is to improve the comfortability of the space using digital signage and the effectiveness of the advertisement to be displayed. So we have developed a system that only reached sound information to people who need it, like people watching a screen. This system is composed of head direction and human position detected by a camera and super directive sound by a parametric speaker. These make the sound volume increase only when the head faces camera, and the speaker to be used is automatically selected according to the position of the person. Because of the super directive sound, it is designed not to be outputted to anyone who does not need it. The experiment using the system was conducted. Compared to the conventional loudspeaker, this system has improved space comfortability while maintaining advertising effect. This suggests that this system can create a more comfortable environment for customers.
{"title":"Effect of Attention Adaptive Personal Audio Deliverable System on Digital Signage","authors":"N. Kuratomo, Kazuki Yamada, Soh Masuko, T. Yamanaka, K. Zempo","doi":"10.1145/3355088.3365171","DOIUrl":"https://doi.org/10.1145/3355088.3365171","url":null,"abstract":"The purpose of this study is to improve the comfortability of the space using digital signage and the effectiveness of the advertisement to be displayed. So we have developed a system that only reached sound information to people who need it, like people watching a screen. This system is composed of head direction and human position detected by a camera and super directive sound by a parametric speaker. These make the sound volume increase only when the head faces camera, and the speaker to be used is automatically selected according to the position of the person. Because of the super directive sound, it is designed not to be outputted to anyone who does not need it. The experiment using the system was conducted. Compared to the conventional loudspeaker, this system has improved space comfortability while maintaining advertising effect. This suggests that this system can create a more comfortable environment for customers.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124270484","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}
Seung Joon Lee, Keon-Woo Kang, Suk-ju Kang, Siyeong Lee
Existing deep learning-based object transfiguration methods are based on unsupervised image-to-image translation which shows reasonable performance. However, previous methods often fail in tasks where the shape of an object changes significantly. In addition, the shape and texture of an original object remain in the converted image. To address these issues, we propose a novel method that decomposes an object transfiguration task into two subtasks: object removal and object synthesis. This prevents an original object from affecting a generated object and makes the generated object better suited to the background. Then, we explicitly formulate each task distinguishing a background and an object using instance information (e.g. object segmentation masks). Our model is unconstrained by position, shape, and size of an original object compared to other methods. We show qualitative and quantitative comparisons with other methods demonstrating the effectiveness of the proposed method.
{"title":"A Decomposition Method of Object Transfiguration","authors":"Seung Joon Lee, Keon-Woo Kang, Suk-ju Kang, Siyeong Lee","doi":"10.1145/3355088.3365151","DOIUrl":"https://doi.org/10.1145/3355088.3365151","url":null,"abstract":"Existing deep learning-based object transfiguration methods are based on unsupervised image-to-image translation which shows reasonable performance. However, previous methods often fail in tasks where the shape of an object changes significantly. In addition, the shape and texture of an original object remain in the converted image. To address these issues, we propose a novel method that decomposes an object transfiguration task into two subtasks: object removal and object synthesis. This prevents an original object from affecting a generated object and makes the generated object better suited to the background. Then, we explicitly formulate each task distinguishing a background and an object using instance information (e.g. object segmentation masks). Our model is unconstrained by position, shape, and size of an original object compared to other methods. We show qualitative and quantitative comparisons with other methods demonstrating the effectiveness of the proposed method.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121824865","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}
We present a ray guiding technique for improving the computation times in the context of production lightmap baking. Compared to state-of-the-art, our method has better scalability and lower variance.
{"title":"Ray Guiding for Production Lightmap Baking","authors":"Ari Silvennoinen, Peter-Pike J. Sloan","doi":"10.1145/3355088.3365167","DOIUrl":"https://doi.org/10.1145/3355088.3365167","url":null,"abstract":"We present a ray guiding technique for improving the computation times in the context of production lightmap baking. Compared to state-of-the-art, our method has better scalability and lower variance.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129831799","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：