J. Spjut, Ben Boudaoud, Kamran Binaee, Jonghyun Kim, Alexander Majercik, M. McGuire, D. Luebke, Joohwan Kim
In competitive sports, human performance makes the difference between who wins and loses. In some competitive video games (esports), response time is an essential factor of human performance. When the athlete’s equipment (computer, input and output device) responds with lower latency, it provides a measurable advantage. In this study, we isolate latency and refresh rate by artificially increasing latency when operating at high refresh rates. Eight skilled esports athletes then perform gaming-inspired first person targeting tasks under varying conditions of refresh rate and latency, completing the tasks as quickly as possible. We show that reduced latency has a clear benefit in task completion time while increased refresh rate has relatively minor effects on performance when the inherent latency reduction present at high refresh rates is removed. Additionally, for certain tracking tasks, there is a small, but marginally significant effect from high refresh rates alone.
{"title":"Latency of 30 ms Benefits First Person Targeting Tasks More Than Refresh Rate Above 60 Hz","authors":"J. Spjut, Ben Boudaoud, Kamran Binaee, Jonghyun Kim, Alexander Majercik, M. McGuire, D. Luebke, Joohwan Kim","doi":"10.1145/3355088.3365170","DOIUrl":"https://doi.org/10.1145/3355088.3365170","url":null,"abstract":"In competitive sports, human performance makes the difference between who wins and loses. In some competitive video games (esports), response time is an essential factor of human performance. When the athlete’s equipment (computer, input and output device) responds with lower latency, it provides a measurable advantage. In this study, we isolate latency and refresh rate by artificially increasing latency when operating at high refresh rates. Eight skilled esports athletes then perform gaming-inspired first person targeting tasks under varying conditions of refresh rate and latency, completing the tasks as quickly as possible. We show that reduced latency has a clear benefit in task completion time while increased refresh rate has relatively minor effects on performance when the inherent latency reduction present at high refresh rates is removed. Additionally, for certain tracking tasks, there is a small, but marginally significant effect from high refresh rates alone.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"2 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":"123313801","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}
Moonwon Yu, Byungjun Kwon, Jongmin Kim, Shinjin Kang, Hanyoung Jang
We propose a fast motion adaptation framework using deep neural networks. Traditionally, motion adaptation is performed via iterative numerical optimization. We adopted deep neural networks and replaced the iterative process with the feed-forward inference consisting of simple matrix multiplications. For efficient mapping from contact constraints to character motion, the proposed system is composed of two types of networks: trajectory and pose generators. The networks are trained using augmented motion capture data and are fine-tuned using the inverse kinematics loss. In experiments, our system successfully generates multi-contact motions of a hundred of characters in real-time, and the result motions contain the naturalness existing in the motion capture data.
{"title":"Fast Terrain-Adaptive Motion Generation using Deep Neural Networks","authors":"Moonwon Yu, Byungjun Kwon, Jongmin Kim, Shinjin Kang, Hanyoung Jang","doi":"10.1145/3355088.3365157","DOIUrl":"https://doi.org/10.1145/3355088.3365157","url":null,"abstract":"We propose a fast motion adaptation framework using deep neural networks. Traditionally, motion adaptation is performed via iterative numerical optimization. We adopted deep neural networks and replaced the iterative process with the feed-forward inference consisting of simple matrix multiplications. For efficient mapping from contact constraints to character motion, the proposed system is composed of two types of networks: trajectory and pose generators. The networks are trained using augmented motion capture data and are fine-tuned using the inverse kinematics loss. In experiments, our system successfully generates multi-contact motions of a hundred of characters in real-time, and the result motions contain the naturalness existing in the motion capture data.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"753 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":"122978315","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}
While performance-based facial animation efficiently produces realistic animation, it still needs additional editing after automatic solving and retargeting. We review why additional editing is required and present a set of interactive editing solutions for VFX studios. The presented solutions allow artists to enhance the result of the automatic solve-retarget with a few tweaks. The methods are integrated into our performance-based facial animation framework and have been actively used in high-quality movie production.
{"title":"Interactive editing of performance-based facial animation","authors":"Yeongho Seol, M. Cozens","doi":"10.1145/3355088.3365147","DOIUrl":"https://doi.org/10.1145/3355088.3365147","url":null,"abstract":"While performance-based facial animation efficiently produces realistic animation, it still needs additional editing after automatic solving and retargeting. We review why additional editing is required and present a set of interactive editing solutions for VFX studios. The presented solutions allow artists to enhance the result of the automatic solve-retarget with a few tweaks. The methods are integrated into our performance-based facial animation framework and have been actively used in high-quality movie production.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"24 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":"122020989","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 novel structure-aware strategy for image expansion which aims to complete an image from a small patch. Different from image inpainting, the majority of the pixels are absent here. Hence, there are higher requirements for global structure-aware prediction to produce visually plausible results. Thus, treating the expansion tasks as inpainting from the outside is ill-posed. Therefore, we propose a learning-based method combining structure-aware and visual attention strategies to make better prediction. Our architecture consists of two stages. Since visual attention cannot be taken full advantage of when the global structure is absent, we first use the ImageNet-pre-trained VGG-19 to make the structure-aware prediction on the pre-training stage. Then, we implement a non-local attention layer on the coarsely-completed results on the refining stage. Our network can well predict the global structures and semantic details from small input image patches, and generate full images with structural consistency. We apply our method on a human face dataset, which containing rich semantic and structural details. The results show its stability and effectiveness.
{"title":"Structure-Aware Image Expansion with Global Attention","authors":"Dewen Guo, J. Feng, Bingfeng Zhou","doi":"10.1145/3355088.3365161","DOIUrl":"https://doi.org/10.1145/3355088.3365161","url":null,"abstract":"We present a novel structure-aware strategy for image expansion which aims to complete an image from a small patch. Different from image inpainting, the majority of the pixels are absent here. Hence, there are higher requirements for global structure-aware prediction to produce visually plausible results. Thus, treating the expansion tasks as inpainting from the outside is ill-posed. Therefore, we propose a learning-based method combining structure-aware and visual attention strategies to make better prediction. Our architecture consists of two stages. Since visual attention cannot be taken full advantage of when the global structure is absent, we first use the ImageNet-pre-trained VGG-19 to make the structure-aware prediction on the pre-training stage. Then, we implement a non-local attention layer on the coarsely-completed results on the refining stage. Our network can well predict the global structures and semantic details from small input image patches, and generate full images with structural consistency. We apply our method on a human face dataset, which containing rich semantic and structural details. The results show its stability and effectiveness.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"27 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":"133233180","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}
Although 3D texture painting has an advantage of making it easy to grasp the overall shape compared with a method of drawing directly onto a UV map, a disadvantage is unpainted (or distorted) regions appearing in the result due to, for example, self-occluded parts. Thus, in order to perform painting without leaving unpainted parts, sequential change of viewpoints is necessary. However, this process is highly time-consuming. To address this problem, we propose an automatic suggestion of optimal viewpoints for 3D texture painting. As the user paints a model, the system searches for optimal viewpoints for subsequent painting and presents them as multiple suggestions. The user switches to a suggested viewpoint by clicking on a suggestion. We conducted a user study and confirmed that the proposed workflow was effective for 3D texture painting envisioned by users.
{"title":"PaintersView: Automatic Suggestion of Optimal Viewpoints for 3D Texture Painting","authors":"Yuka Takahashi, Tsukasa Fukusato, T. Igarashi","doi":"10.1145/3355088.3365159","DOIUrl":"https://doi.org/10.1145/3355088.3365159","url":null,"abstract":"Although 3D texture painting has an advantage of making it easy to grasp the overall shape compared with a method of drawing directly onto a UV map, a disadvantage is unpainted (or distorted) regions appearing in the result due to, for example, self-occluded parts. Thus, in order to perform painting without leaving unpainted parts, sequential change of viewpoints is necessary. However, this process is highly time-consuming. To address this problem, we propose an automatic suggestion of optimal viewpoints for 3D texture painting. As the user paints a model, the system searches for optimal viewpoints for subsequent painting and presents them as multiple suggestions. The user switches to a suggested viewpoint by clicking on a suggestion. We conducted a user study and confirmed that the proposed workflow was effective for 3D texture painting envisioned by users.","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":"130296304","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}
Recent studies on planar scene modeling from a single image employ multi-branch neural networks to simultaneously segment pla-nes and recover 3D plane parameters. However, the generalizability and accuracy of these supervised methods heavily rely on the scale of available annotated data. In this paper, we propose multi-view regularization for network training to further enhance single-view reconstruction networks, without demanding extra annotated data. Our multi-view regularization emphasizes multi-view consistency in the training phase, making the feature embedding more robust against view change and lighting variation. Thus, the neural network trained with our regularization can be better generalized to a wide range of views and lightings. Our method achieves state-of-the-art reconstruction performance compared to previous piecewise planar reconstruction methods on the public ScanNet dataset.
{"title":"Enhancing Piecewise Planar Scene Modeling from a Single Image via Multi-View Regularization","authors":"Weijie Xi, Siyu Hu, X. Chen, Zhiwei Xiong","doi":"10.1145/3355088.3365152","DOIUrl":"https://doi.org/10.1145/3355088.3365152","url":null,"abstract":"Recent studies on planar scene modeling from a single image employ multi-branch neural networks to simultaneously segment pla-nes and recover 3D plane parameters. However, the generalizability and accuracy of these supervised methods heavily rely on the scale of available annotated data. In this paper, we propose multi-view regularization for network training to further enhance single-view reconstruction networks, without demanding extra annotated data. Our multi-view regularization emphasizes multi-view consistency in the training phase, making the feature embedding more robust against view change and lighting variation. Thus, the neural network trained with our regularization can be better generalized to a wide range of views and lightings. Our method achieves state-of-the-art reconstruction performance compared to previous piecewise planar reconstruction methods on the public ScanNet dataset.","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":"130678738","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}
S. Zollmann, T. Langlotz, Moritz Loos, Wei Hong Lo, Lewis Baker
Augmented Reality (AR) has gained a lot of interests recently and has been used for various applications. Most of these applications are however limited to small indoor environments. Despite the wide range of large scale application areas that could highly benefit from AR usage, until now there are rarely AR applications that target such environments. In this work, we discuss how AR can be used to enhance the experience of on-site spectators at live sport events. We investigate the challenges that come with applying AR for such a large scale environment and explore state-of-the-art technology and its suitability for an on-site AR spectator experience. We also present a concept design and explore the options to implement AR applications inside large scale environments.
{"title":"ARSpectator: Exploring Augmented Reality for Sport Events","authors":"S. Zollmann, T. Langlotz, Moritz Loos, Wei Hong Lo, Lewis Baker","doi":"10.1145/3355088.3365162","DOIUrl":"https://doi.org/10.1145/3355088.3365162","url":null,"abstract":"Augmented Reality (AR) has gained a lot of interests recently and has been used for various applications. Most of these applications are however limited to small indoor environments. Despite the wide range of large scale application areas that could highly benefit from AR usage, until now there are rarely AR applications that target such environments. In this work, we discuss how AR can be used to enhance the experience of on-site spectators at live sport events. We investigate the challenges that come with applying AR for such a large scale environment and explore state-of-the-art technology and its suitability for an on-site AR spectator experience. We also present a concept design and explore the options to implement AR applications inside large scale environments.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"44 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":"123103186","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}
Nicolas Nghiem, R. Roberts, J. P. Lewis, Jun-yong Noh
Keyframes are a core notion used by animators to understand and describe the motion. In this paper, we take inspiration from keyframe animation to compute a feature that we call the “Saliency diagram” of the animation. To create our saliency diagrams, we visualize how often each frame becomes a keyframe when using an existing selection technique. Animators can use the resulting Saliency diagram to analyze the motion.
{"title":"Saliency Diagrams","authors":"Nicolas Nghiem, R. Roberts, J. P. Lewis, Jun-yong Noh","doi":"10.1145/3355088.3365155","DOIUrl":"https://doi.org/10.1145/3355088.3365155","url":null,"abstract":"Keyframes are a core notion used by animators to understand and describe the motion. In this paper, we take inspiration from keyframe animation to compute a feature that we call the “Saliency diagram” of the animation. To create our saliency diagrams, we visualize how often each frame becomes a keyframe when using an existing selection technique. Animators can use the resulting Saliency diagram to analyze the motion.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"14 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":"133087369","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}
T. AakashK., P. Sakurikar, Saurabh Saini, P J Narayanan
Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene. The workflow for material modeling and editing typically involves manual tweaking of material parameters and uses a standard path tracing engine for visual feedback. A lot of time may be spent in iterative selection and rendering of materials at an appropriate quality. In this work, we propose a convolutional neural network that quickly generates high-quality ray traced material visualizations on a shaderball. Our novel architecture allows for control over environment lighting which assists in material selection and also provides the ability to render spatially-varying materials. Comparison with state-of-the-art denoising and neural rendering techniques suggests that our neural renderer performs faster and better. We provide an interactive visualization tool and an extensive dataset to foster further research in this area.
{"title":"A Flexible Neural Renderer for Material Visualization","authors":"T. AakashK., P. Sakurikar, Saurabh Saini, P J Narayanan","doi":"10.1145/3355088.3365160","DOIUrl":"https://doi.org/10.1145/3355088.3365160","url":null,"abstract":"Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene. The workflow for material modeling and editing typically involves manual tweaking of material parameters and uses a standard path tracing engine for visual feedback. A lot of time may be spent in iterative selection and rendering of materials at an appropriate quality. In this work, we propose a convolutional neural network that quickly generates high-quality ray traced material visualizations on a shaderball. Our novel architecture allows for control over environment lighting which assists in material selection and also provides the ability to render spatially-varying materials. Comparison with state-of-the-art denoising and neural rendering techniques suggests that our neural renderer performs faster and better. We provide an interactive visualization tool and an extensive dataset to foster further research in this area.","PeriodicalId":435930,"journal":{"name":"SIGGRAPH Asia 2019 Technical Briefs","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132271514","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：