发布求助
文献互助 智能选刊 最新文献

SIGGRAPH Asia 2013 Technical Briefs最新文献

筛选
英文 中文
Learning based compression of surface light fields for real-time rendering of global illumination scenes 基于学习的表面光场压缩用于全局照明场景的实时渲染
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542385
Ehsan Miandji, J. Kronander, J. Unger
{"title":"Learning based compression of surface light fields for real-time rendering of global illumination scenes","authors":"Ehsan Miandji, J. Kronander, J. Unger","doi":"10.1145/2542355.2542385","DOIUrl":"https://doi.org/10.1145/2542355.2542385","url":null,"abstract":"We present an algorithm for compression and real-time rendering of surface light fields (SLF) encoding the visual appearance of objects in static scenes with high frequency variations. We apply a non-local clustering in order to exploit spatial coherence in the SLF data. To efficiently encode the data in each cluster, we introduce a learning based approach, Clustered Exemplar Orthogonal Bases (CEOB), which trains a compact dictionary of orthogonal basis pairs, enabling efficient sparse projection of the SLF data. In addition, we discuss the application of the traditional Clustered Principal Component Analysis (CPCA) on SLF data, and show that in most cases, CEOB outperforms CPCA, K-SVD and spherical harmonics in terms of memory footprint, rendering performance and reconstruction quality. Our method enables efficient reconstruction and real-time rendering of scenes with complex materials and light sources, not possible to render in real-time using previous methods.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122590957","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}
引用次数: 12
MultiMosaic: simultaneous visualization of multiple images for near and far viewers using image mosaic and saliency map 多重马赛克:使用图像马赛克和显著性地图为近距离和远距离的观众同时可视化多个图像
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542379
Yuta Suzuki, H. Koike
{"title":"MultiMosaic: simultaneous visualization of multiple images for near and far viewers using image mosaic and saliency map","authors":"Yuta Suzuki, H. Koike","doi":"10.1145/2542355.2542379","DOIUrl":"https://doi.org/10.1145/2542355.2542379","url":null,"abstract":"This paper presents a method to display two types of images simultaneously in one image. One is for viewers at a far distance, and the other is for viewers closer to the screen. The basic idea is to overlay small images in high resolution (i.e. near-images) on a larger image in low resolution (i.e. far-image) by adjusting transparency of the near images. However, this simple overlay approach fails to provide acceptable visibility for both images. We propose to use a saliency map to emphasize important features of each image. By using this saliency map, it is possible to provide better visibility for both images, which this paper will illustrate with various examples.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114559980","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}
引用次数: 0
Example-based art pattern synthesis using level sets 使用关卡集合成基于实例的美术模式
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542363
Ruobing Wu, Wenping Wang, Yizhou Yu
{"title":"Example-based art pattern synthesis using level sets","authors":"Ruobing Wu, Wenping Wang, Yizhou Yu","doi":"10.1145/2542355.2542363","DOIUrl":"https://doi.org/10.1145/2542355.2542363","url":null,"abstract":"Line drawings and digital arts appear everywhere, from simple icons to cartoons, maps and illustrations. We define art patterns as the subset of line drawings and digital arts that are comprised of repeated elements. Inspired by recent success of exemplar-based texture synthesis, in this paper, we focus on synthesizing art patterns with curvilinear features from exemplars, which we cast as a global optimization problem. Our energy function for this problem measures both the appearance similarity of color patterns and shape similarity of curvilinear features. We develop an overall EM-style algorithm for minimizing this energy function. The shape similarity part of the energy is minimized through an innovative application of the level set method. We further generalize our energy function and optimization algorithm so that they can effectively synthesize art patterns that consist of multiple layers.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115959381","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}
引用次数: 0
Computer analysis for visual art style 视觉艺术风格的计算机分析
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542366
Yuqing Liu, Yuanyuan Pu, Dan Xu
{"title":"Computer analysis for visual art style","authors":"Yuqing Liu, Yuanyuan Pu, Dan Xu","doi":"10.1145/2542355.2542366","DOIUrl":"https://doi.org/10.1145/2542355.2542366","url":null,"abstract":"In recent years, scholars pay more and more attention to the understanding and analysis of visual art style. This paper is based on Sparse Coding on visual art works, which brings out the trained basis function reflecting the style characteristics of a painting. Next, Gabor energy is extracted in Gabor domain from the trained basis function. Van Gogh's art works of different periods and Monet's art works are analyzed through normalized mutual information computing using trained basis function's Gabor energy to find the diversity of style. The experiment results show that Gabor energy can digitalize the intuitive feeling for basis function, and can distinguish the art styles of different works to a certain extent, and finally can provide reference for the criticism of art works.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127467421","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}
引用次数: 4
Generating multi-style paper pop-up designs using 3D primitive fitting 使用3D原始拟合生成多风格的纸弹出设计
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542360
Conrado R. Ruiz, Sang N. Le, Kok-Lim Low
{"title":"Generating multi-style paper pop-up designs using 3D primitive fitting","authors":"Conrado R. Ruiz, Sang N. Le, Kok-Lim Low","doi":"10.1145/2542355.2542360","DOIUrl":"https://doi.org/10.1145/2542355.2542360","url":null,"abstract":"Paper pop-ups are fascinating three-dimensional books that impart stories and information more vividly to their readers. The design and construction of these pop-up books, however, are generally done by hand, and given the lack of expertise in this area, have necessitated the need for automated or computer-assisted design of paper pop-ups. This paper presents an automatic algorithm and the underlying theory for producing paper pop-up designs from 3D models. Existing studies on paper pop-ups have mainly focused on individual styles and proposed formulations for only a limited set of mechanisms. In our work, we design multi-style pop-ups by combining the formulations of previously studied styles with our derived validity conditions for box-style pop-ups. We use a mesh abstraction technique that fits volumetric primitives unto a 3D mesh, which are later automatically mapped to selected mechanisms. We also preserve important texture and shape contours using a hybrid object- and image-space approach. Finally, we generate printable design layouts and the corresponding assembly instructions to facilitate the actual production, which verifies the feasibility of our pop-ups.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133514013","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}
引用次数: 2
A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting 一种基于模式的图像绘制中伪影减少的快速空间斑块混合算法
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542365
M. Daisy, D. Tschumperlé, O. Lézoray
{"title":"A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting","authors":"M. Daisy, D. Tschumperlé, O. Lézoray","doi":"10.1145/2542355.2542365","DOIUrl":"https://doi.org/10.1145/2542355.2542365","url":null,"abstract":"We propose a fast and generic spatial patch blending technique that can be embedded within any kind of pattern-based inpainting algorithm. This extends our previous work on the visual enhancement of inpainting results. We optimize this blending algorithm so that the processing time is roughly divided by a factor ten, without any loss of perceived quality. Moreover, we provide an open-source and simple-to-use software to make this easily reproducible.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132577883","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}
引用次数: 31
Mining effective parallelism from hidden coherence for GPU based path tracing 基于GPU的路径跟踪中隐藏相干性的有效并行性挖掘
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542394
Tong Wang, Yangdong Deng
{"title":"Mining effective parallelism from hidden coherence for GPU based path tracing","authors":"Tong Wang, Yangdong Deng","doi":"10.1145/2542355.2542394","DOIUrl":"https://doi.org/10.1145/2542355.2542394","url":null,"abstract":"As one of the essential global illumination algorithms, Monte Carlo path tracing has long been considered as a typical irregular problem that is less friendly for graphics hardware. To improve the efficiency of Monte Carlo path tracing, such techniques as ray reordering, ray compaction and wavefront formulation have been proposed to exploit the inherent coherence in processing different paths and materials for better SIMD efficiency on GPUs. In this paper, we develop a novel technique to extract extra parallelism in Monte Carlo path tracing applications by identifying hidden coherence. The basic idea is to perform a partial traversal in the fast on-chip memory of GPU and then identify coherent paths by analyzing the traversal results as well as other features of rays. Such coherence enables a higher level of parallelism that not only compensates the overhead of traversal, but also leads to improved performance. Experiments prove that our techniques deliver a traversal throughput higher than leading-edge results by up to 15%.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131834772","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}
引用次数: 3
Parallel divide and conquer ray tracing 平行分治光线追踪
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542393
S. Ravichandran, P J Narayanan
{"title":"Parallel divide and conquer ray tracing","authors":"S. Ravichandran, P J Narayanan","doi":"10.1145/2542355.2542393","DOIUrl":"https://doi.org/10.1145/2542355.2542393","url":null,"abstract":"Divide and Conquer Ray Tracing (DACRT) is a recent technique which constructs no explicit acceleration structure. It creates and traverses an implicit hierarchy in a depth-first fashion recursively and is suited for dynamic scenes that change constantly. In this paper, we present a parallel version of DACRT that runs entirely on the GPU, which exploits efficient primitives like sort and reduce. Our approach suits the GPU well, with a low memory footprint. Our implementation outperforms the serial CPU algorithm for both primary and secondary ray passes. We show good performance on primary pass and on advanced effects.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133074978","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}
引用次数: 3
Decolorization: is rgb2gray() out? 脱色:rgb2gray()脱色了吗?
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542374
Yibing Song, Linchao Bao, Xiaobin Xu, Qingxiong Yang
{"title":"Decolorization: is rgb2gray() out?","authors":"Yibing Song, Linchao Bao, Xiaobin Xu, Qingxiong Yang","doi":"10.1145/2542355.2542374","DOIUrl":"https://doi.org/10.1145/2542355.2542374","url":null,"abstract":"Decolorization problems originate from the fact that the luminance channel may fail to represent iso-luminant regions in the original color image. Currently all the existing methods suffer from the same weakness -- robustness: failure cases can be easily found for each of the methods. This prevents all these methods from being practical for real-world applications. In fact, the luminance conversion (i.e, rgb2gray() function in Matlab) performs rather well in practice only with exceptions for failure cases like the iso-luminant regions. Thus a thought-provoking question is naturally raised: can we reach a robust solution by simply modifying the rgb2gray() to avoid failures in iso-luminant regions? Instead of assigning fixed channel weights for all images, a more flexible strategy would be choosing channel weights depending on specific images to avoid indiscrimination in iso-luminant regions. Following this strategy, by considering multi-scale contrast preservation, we design an algorithm that can consistently produce \"good\" results for each color image, among which the \"best\" one preferred by users can be selected by further involving perceptual contrasts preferences. The results are verified through user study.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127462714","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}
引用次数: 44
Data-driven suggestions for portrait posing 数据驱动的肖像造型建议
SIGGRAPH Asia 2013 Technical Briefs Pub Date : 2013-11-19 DOI: 10.1145/2542355.2542391
Hongbo Fu, Xiaoguang Han, Quoc Huy Phan
{"title":"Data-driven suggestions for portrait posing","authors":"Hongbo Fu, Xiaoguang Han, Quoc Huy Phan","doi":"10.1145/2542355.2542391","DOIUrl":"https://doi.org/10.1145/2542355.2542391","url":null,"abstract":"Next to lighting, posing is the most challenging aspect of portrait photography. A commonly adopted solution is to learn by example, which is beneficial for both trained photographers and novice users, especially when subjects have no clue about how to pose themselves. A collection of portrait images by professionals (e.g., [Perkins 2009]) provides a resource for photographers seeking inspiration for their own work. Such handful posing references (e.g., Posing App) have also been made available to smartphone platforms, which offer the unique possibility of directly overlaying camera view with a reference pose as visual guidance.","PeriodicalId":232593,"journal":{"name":"SIGGRAPH Asia 2013 Technical Briefs","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131034599","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}
引用次数: 13
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信