ACM SIGGRAPH 2014 Talks最新文献_第5页

Adaptive rendering based on weighted local regression 基于加权局部回归的自适应渲染

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614160

Bochang Moon, N. Carr, Sung-eui Yoon

{"title":"Adaptive rendering based on weighted local regression","authors":"Bochang Moon, N. Carr, Sung-eui Yoon","doi":"10.1145/2614106.2614160","DOIUrl":"https://doi.org/10.1145/2614106.2614160","url":null,"abstract":"Monte Carlo ray tracing is considered one of the most effective techniques for rendering photo-realistic imagery, but requires a large number of ray samples to produce converged or even visually pleasing images. We develop a novel image-plane adaptive sampling and reconstruction method based on local regression theory. A novel local space estimation process is proposed for employing the local regression, by robustly addressing noisy high-dimensional features. Given the local regression on estimated local space, we provide a novel two-step optimization process for selecting band-widths of features locally in a data-driven way. Local weighted regression is then applied using the computed bandwidths to produce a smooth image reconstruction with well-preserved details. We derive an error analysis to guide our adaptive sampling process at the local space. We demonstrate that our method produces more accurate and visually pleasing results over the state-of-the-art techniques across a wide range of rendering effects. Our method also allows users to employ an arbitrary set of features, including noisy features, and robustly computes a subset of them by ignoring noisy features and decorrelating them for higher quality. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org.","PeriodicalId":118349,"journal":{"name":"ACM SIGGRAPH 2014 Talks","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129818994","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: 21

Dynamic on-mesh procedural generation control 动态网格上程序生成控制

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614129

C. Buron, Jean-Eudes Marvie, Gaël Guennebaud, Xavier Granier

引用次数: 0

DreamWorks animation's face system, a historical perspective: from ANTZ and Shrek to Mr Peabody & Sherman 梦工厂动画的人脸系统，一个历史的视角:从ANTZ和史莱克到皮博迪和谢尔曼

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614131

L. Modesto, D. Walsh

引用次数: 1

A dual-beam 3D searchlight BSSRDF 双光束三维探照灯BSSRDF

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614140

Eugene d'Eon

引用次数: 13

Level of detail in an age of GI: rethinking crowd rendering GI时代的细节水平:重新思考人群渲染

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614119

Paul Kanyuk

引用次数: 1

Building highly parallel character rigs 构建高度平行的角色装备

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614154

Guido Zimmermann, Kevin Ochs, R. Helms

引用次数: 1

Creating a life-sized automultiscopic Morgan Spurlock for CNNs "Inside Man" 为cnn《内幕》制作真人大小的自动多镜摩根·斯普尔洛克

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614177

Andrew Jones, J. Unger, Koki Nagano, Jay Busch, Xueming Yu, H. Peng, O. Alexander, P. Debevec

{"title":"Creating a life-sized automultiscopic Morgan Spurlock for CNNs \"Inside Man\"","authors":"Andrew Jones, J. Unger, Koki Nagano, Jay Busch, Xueming Yu, H. Peng, O. Alexander, P. Debevec","doi":"10.1145/2614106.2614177","DOIUrl":"https://doi.org/10.1145/2614106.2614177","url":null,"abstract":"We present a system for capturing and rendering life-size 3D human subjects on an automultiscopic display. Automultiscopic 3D displays allow a large number of viewers to experience 3D content simultaneously without the hassle of special glasses or head gear. Such displays are ideal for human subjects as they allow for natural personal interactions with 3D cues such as eye-gaze and complex hand gestures. In this talk, we will focus on a case-study where our system was used to digitize television host Morgan Spurlock for his documentary show ”Inside Man” on CNN. Automultiscopic displays work by generating many simultaneous views with highangular density over a wide-field of view. The angular spacing between between views must be small enough that each eye perceives a distinct and different view. As the user moves around the display, the eye smoothly transitions from one view to the next. We generate multiple views using a dense horizontal array of video projectors. As video projectors continue to shrink in size, power consumption, and cost, it is now possible to closely stack hundreds of projectors so that their lenses are almost continuous. However this display presents a new challenge for content acquisition. It would require hundreds of cameras to directly measure every projector ray. We achieve similar quality with a new view interpolation algorithm suitable for dense automultiscopic displays.","PeriodicalId":118349,"journal":{"name":"ACM SIGGRAPH 2014 Talks","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123470325","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

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614117

Pascal Gautron, M. Droske, Carsten Wächter, Lutz Kettner, A. Keller, Nikolaus Binder, Ken Dahm

引用次数: 9

Capturing the infinite universe in "Lucy": fractal rendering in film production 在《露西》中捕捉无限宇宙:电影制作中的分形渲染

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614166

Alex Kim, D. P. Ferreira, Stephen Bevins

{"title":"Capturing the infinite universe in \"Lucy\": fractal rendering in film production","authors":"Alex Kim, D. P. Ferreira, Stephen Bevins","doi":"10.1145/2614106.2614166","DOIUrl":"https://doi.org/10.1145/2614106.2614166","url":null,"abstract":"There are several existing fractal renderers that can create high quality images, e.g. ultra-fractal, mandelbulber, xenodream, Fractal Explorer. While these renderers focus on computational performance and image quality, they tend to overlook factors like layout and interaction with other elements/simulations as well as pipeline integration, all of which are essential to movie production. The creation of explicit geometry for highly detailed fractals can quickly result in meshes with overwhelming polygon counts, and consequently most production renderers, e.g. Mantra, will run out of memory during the construction of the associated mesh acceleration data structures. To address these shortcomings we propose a novel approach to production rendering of detailed fractals. Our technique, which is based on a hybrid particle/OpenVDB representation, can render fractals with very high details while incurring a small memory footprint. Additionally our approach is easily parallelizable across multiple machines, allows for a quick viewport preview for layout, can utilize existing production lights/shaders, can produce proxy meshes for interactions with simulations, and supports volume rendering.","PeriodicalId":118349,"journal":{"name":"ACM SIGGRAPH 2014 Talks","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125698822","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

High level saliency prediction for smart game balancing 智能游戏平衡的高水平显著性预测

ACM SIGGRAPH 2014 Talks Pub Date : 2014-07-27 DOI: 10.1145/2614106.2614157

G. Koulieris, G. Drettakis, D. Cunningham, K. Mania

{"title":"High level saliency prediction for smart game balancing","authors":"G. Koulieris, G. Drettakis, D. Cunningham, K. Mania","doi":"10.1145/2614106.2614157","DOIUrl":"https://doi.org/10.1145/2614106.2614157","url":null,"abstract":"Predicting visual attention can significantly improve scene design, interactivity and rendering. For example, image synthesis can be accelerated by reducing computation on non-attended scene regions; attention can also be used to improve LOD. Most previous attention models are based on low-level image features, as it is computationally and conceptually challenging to take into account highlevel factors such as scene context, topology or task. As a result, they often fail to predict saccadic targets because scene semantics strongly affect the planning and execution of fixations. In this talk, we present the first automated high level saliency predictor that incorporates the schema [Bartlett 1932] and singleton [Theeuwes and Godijn 2002] hypotheses into the Differential-Weighting Model (DWM) [Eckstein 1998]. The scene schema effect states that a scene is comprised of objects expected to be found in a specific context as well objects out of context which are salient (Figure 1a). The singleton effect refers to the finding that viewer’s attention is captured by isolated objects (Figure 1b). We propose a new model to account for high-level object saliency as predicted by the schema and singleton hypotheses by extending the DWM. The DWM models attentional processing using physiological noise in brain neurons and Gaussian combination rules. A GPU implementation of our model estimates the probabilities of individual objects to be foveated and is used in an innovative game level editor that automatically suggests game objects’ positioning. The difficulty of a game can then be implicitly adjusted since topology affects object search completion time.","PeriodicalId":118349,"journal":{"name":"ACM SIGGRAPH 2014 Talks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126971584","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