Proceedings. Pacific Conference on Computer Graphics and Applications最新文献_第3页

Peripheral Vision in Simulated Driving: Comparing CAVE and Head-mounted Display 模拟驾驶中的周边视觉:比较CAVE和头戴式显示器

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/PG.20211392

Tana Tanoi, N. Dodgson

引用次数: 0

View-Dependent Impostors for Architectural Shape Grammars 建筑形状语法的视图依赖的冒名顶替者

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/pg.20211390

Chao Jia, Moritz Roth, B. Kerbl, M. Wimmer

引用次数: 1

CSLF: Cube Surface Light Field and Its Sampling, Compression, Real-Time Rendering 立方体表面光场及其采样、压缩、实时渲染

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/pg.20211381

Xiao Ai, Yigang Wang, Simin Kou

{"title":"CSLF: Cube Surface Light Field and Its Sampling, Compression, Real-Time Rendering","authors":"Xiao Ai, Yigang Wang, Simin Kou","doi":"10.2312/pg.20211381","DOIUrl":"https://doi.org/10.2312/pg.20211381","url":null,"abstract":"Light field is gaining both research and commercial interests since it has the potential to produce view-dependent and photorealistic effects for virtual and augmented reality. In this paper, we further explore the light field and presents a novel parameterization that permits 1) effectively sampling the light field of an object with unknown geometry, 2) efficiently compressing and 3) real-time rendering from arbitrary viewpoints. A novel, key element in our parameterization is that we use the intersections of the light rays and a general cube surface to parameterize the four-dimensional light field, constructing the cube surface light field (CSLF). We resolve the huge data amount problem in CSLF by uniformly decimating the viewpoint space to form a set of key views which are then converted into a pseudo video sequence and compressed using the high efficiency video coding encoder. To render the CSLF, we employ a ray casting approach and draw a polygonal mesh, enabling real-time generating arbitrary views from the outside of the cube surface. We build the CSLF datasets and extensively evaluate our parameterization from the sampling, compression and rendering. Results show that the cube surface parameterization can simultaneously achieve the above three characteristics, indicating the potentiality in practical virtual and augmented reality. CCS Concepts • Computing methodologies → Image-based rendering; Ray tracing; Image compression;","PeriodicalId":88304,"journal":{"name":"Proceedings. Pacific Conference on Computer Graphics and Applications","volume":"62 1","pages":"13-18"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79650445","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

User-centred Depth Estimation Benchmarking for VR Content Creation from Single Images 基于单个图像的VR内容创作的以用户为中心的深度估计基准

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/pg.20211394

Anthony Dickson, Alistair Knott, S. Zollmann

引用次数: 0

Hierarchical Link and Code: Efficient Similarity Search for Billion-Scale Image Sets 层次链接和代码:10亿尺度图像集的高效相似性搜索

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/PG.20211397

Kaixiang Yang, Hongya Wang, Ming-han Du, Zhizheng Wang, Zongyuan Tan, Yingyuan Xiao

{"title":"Hierarchical Link and Code: Efficient Similarity Search for Billion-Scale Image Sets","authors":"Kaixiang Yang, Hongya Wang, Ming-han Du, Zhizheng Wang, Zongyuan Tan, Yingyuan Xiao","doi":"10.2312/PG.20211397","DOIUrl":"https://doi.org/10.2312/PG.20211397","url":null,"abstract":"Similarity search is an indispensable component in many computer vision applications. To index billions of images on a single commodity server, Douze et al. introduced L&C that works on operating points considering 64–128 bytes per vector. While the idea is inspiring, we observe that L&C still suffers the accuracy saturation problem, which it is aimed to solve. To this end, we propose a simple yet effective two-layer graph index structure, together with dual residual encoding, to attain higher accuracy. Particularly, we partition vectors into multiple clusters and build the top-layer graph using the corresponding centroids. For each cluster, a subgraph is created with compact codes of the first-level vector residuals. Such an index structure provides better graph search precision as well as saves quite a few bytes for compression. We employ the second-level residual quantization to re-rank the candidates obtained through graph traversal, which is more efficient than regression-from-neighbors adopted by L&C. Comprehensive experiments show that our proposal obtains over 30% higher recall@1 than the state-of-thearts, and achieves up to 7.7x and 6.1x speedup over L&C on Deep1B and Sift1B, respectively. CCS Concepts • Information systems → Top-k retrieval in databases;","PeriodicalId":88304,"journal":{"name":"Proceedings. Pacific Conference on Computer Graphics and Applications","volume":"76 1","pages":"81-86"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89688741","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: 1

Temporally Stable Content-Adaptive and Spatio-Temporal Shading Rate Assignment for Real-Time Applications 实时应用的时间稳定内容自适应和时空遮阳率分配

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/PG.20211391

S. Stappen, Johannes Unterguggenberger, B. Kerbl, M. Wimmer

引用次数: 0

Neural Screen Space Rendering of Direct Illumination 直接照明的神经屏幕空间渲染

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/pg.20211385

C. Suppan, Andrew Chalmers, Junhong Zhao, A. Doronin, Taehyun Rhee

{"title":"Neural Screen Space Rendering of Direct Illumination","authors":"C. Suppan, Andrew Chalmers, Junhong Zhao, A. Doronin, Taehyun Rhee","doi":"10.2312/pg.20211385","DOIUrl":"https://doi.org/10.2312/pg.20211385","url":null,"abstract":"Neural rendering is a class of methods that use deep learning to produce novel images of scenes from more limited information than traditional rendering methods. This is useful for information scarce applications like mixed reality or semantic photo synthesis but comes at the cost of control over the final appearance. We introduce the Neural Direct-illumination Renderer (NDR), a neural screen space renderer capable of rendering direct-illumination images of any geometry, with opaque materials, under distant illuminant. The NDR uses screen space buffers describing material, geometry, and illumination as inputs to provide direct control over the output. We introduce the use of intrinsic image decomposition to allow a Convolutional Neural Network (CNN) to learn a mapping from a large number of pixel buffers to rendered images. The NDR predicts shading maps, which are subsequently combined with albedo maps to create a rendered image. We show that the NDR produces plausible images that can be edited by modifying the input maps and marginally outperforms the state of the art while also providing more functionality. CCS Concepts • Computing methodologies → Rendering; Neural networks; Supervised learning by regression;","PeriodicalId":88304,"journal":{"name":"Proceedings. Pacific Conference on Computer Graphics and Applications","volume":"22 1","pages":"37-42"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90461582","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

SDALIE-GAN: Structure and Detail Aware GAN for Low-light Image Enhancement SDALIE-GAN:用于弱光图像增强的结构和细节感知GAN

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/PG.20211393

Youxin Pang, Mengke Yuan, Yuchun Chang, Dong‐Ming Yan

引用次数: 0

Maximum-Clearance Planar Motion Planning Based on Recent Developments in Computing Minkowski Sums and Voronoi Diagrams 基于Minkowski和和Voronoi图计算新进展的最大间隙平面运动规划

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/PG.20211382

M. Jung, Myung-Soo Kim

引用次数: 0

Constraint Synthesis for Parametric CAD 参数化CAD的约束综合

Proceedings. Pacific Conference on Computer Graphics and Applications Pub Date : 2021-01-01 DOI: 10.2312/PG.20211396

A. Mathur, D. Zufferey

引用次数: 1