CAREER: Efficient and Realistic Spatial/Temporal Appearance Details
职业:高效、真实的空间/时间外观细节
基本信息
- 批准号:0132970
- 负责人:
- 金额:$ 32.5万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2002
- 资助国家:美国
- 起止时间:2002-01-15 至 2006-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
0132970Yu, YizhouU of Ill - ChampaignThis project addresses the problem of recovering and synthetically generating realistic appearance details. Appearance details include color/reflectance variations, small geometric features on 3D surfaces, and the change of these high-resolution geometric and physical properties at different times. We call these details 3D and temporal textures in contrast to 2D textures which only have color variations in a 2D space. This project describes fundamental research in four classes of problems surrounding 3D and temporal textures:(1) the development of a unified framework for texture modeling considering 3D spatially and temporally varying details;(2) the development of novel algorithms that either recover high-quality appearance details from photographs and videos or generate them synthetically;(3) the development of efficient synthesis algorithms that can generate novel instances of 3D and temporal textures from given examples;(4) the investigation of efficient representation and compression schemes for 3D and temporal textures.This project will result in significant advances in 3D and temporal appearance modeling and synthesis, and therefore lead to overall qualitative improvement of the synthetic imagery created by graphics approaches.3D and temporal textures complement geometric modeling and physical simulation. Addressing the proposed problem will greatly benefit these and other related research directions. Recent advances in physics-based simulation made it possible to generate synthetic imagery from solving light transport and motion equations. While these simulation-based techniques are quite expensive, the results generated from these techniques are often found to be too clean and smooth to look realistic enough. Incorporating appearance details into these methods would be highly desirable. Meanwhile, recent geometric reconstruction techniques from images and laser range scans have made it possible to acquire high-quality geometric models. Appearance modeling is becoming increasingly important in computer graphics applications where the efficient and realistic representation of details is essential. This work will be able to produce statistically correct, physically plausible appearance details in an efficient manner. In the film industry, high-quality hair models and skin surface details will dramatically shrink the gap between synthetic and real characters. In the game industry, real-time 3D and temporal textures will bring virtual environments a large step closer to reality. This holds true for a large number of applications including electronic commerce, TV and Web content production, human computer interaction, architectural and archeological walkthroughs.Altogether, the expected outcome of the project will be the development of important new techniques and results that provide real-world applications with useful solutions, cross-fertilization between computer graphics and other related areas (such as image processing and computer vision), and curricular innovations.
0132970余,YizhouU,Iil-Champaign本项目解决恢复和综合生成逼真的外观细节的问题。 外观细节包括颜色/反射率变化,3D表面上的小几何特征,以及这些高分辨率几何和物理属性在不同时间的变化。我们称这些细节为3D和时间纹理,而2D纹理在2D空间中只有颜色变化。该项目描述了围绕3D和时间纹理的四类问题的基础研究:(1)考虑3D空间和时间变化细节的纹理建模的统一框架的开发;(2)从照片和视频恢复高质量外观细节或合成它们的新算法的开发;(3)开发有效的合成算法,可以从给定的示例生成3D和时间纹理的新实例;(4)三维和时间纹理的有效表示和压缩方案的研究。该项目将导致三维和时间外观建模和合成的重大进展,并因此导致由图形方法创建的合成图像的整体质量改进。3D和时间纹理补充几何建模和物理模拟。 解决所提出的问题将大大有利于这些和其他相关的研究方向。基于物理学的模拟的最新进展使得通过求解光传输和运动方程生成合成图像成为可能。 虽然这些基于模拟的技术非常昂贵,但这些技术生成的结果通常过于干净和平滑,看起来不够逼真。 将外观细节简化到这些方法中将是非常可取的。 与此同时,最近的几何重建技术,从图像和激光距离扫描已经有可能获得高质量的几何模型。外观建模在计算机图形应用中变得越来越重要,其中细节的高效和逼真的表示是必不可少的。 这项工作将能够以有效的方式产生统计上正确的、物理上合理的外观细节。在电影行业,高质量的头发模型和皮肤表面细节将极大地缩小合成人物和真实的人物之间的差距。在游戏行业,实时3D和时间纹理将使虚拟环境更接近现实。这也适用于大量的应用,包括电子商务,电视和网络内容制作,人机交互,建筑和考古walkenches。总之,该项目的预期成果将是重要的新技术和成果的发展,为现实世界的应用提供有用的解决方案,计算机图形学和其他相关领域(如图像处理和计算机视觉)之间的交叉施肥,以及课程创新。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Yizhou Yu其他文献
Medical Volume Segmentation based on Level Sets of Probabilities
基于概率水平集的医疗体积分割
- DOI:
10.5220/0004185903870394 - 发表时间:
2013 - 期刊:
- 影响因子:0
- 作者:
Yugang Liu;Yizhou Yu - 通讯作者:
Yizhou Yu
Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance
具有属性推理辅助的计算机辅助结核病诊断
- DOI:
10.48550/arxiv.2207.00251 - 发表时间:
2022 - 期刊:
- 影响因子:0
- 作者:
C. Pan;Gangming Zhao;Junjie Fang;Baolian Qi;Jiaheng Liu;Chaowei Fang;Dingwen Zhang;Jinpeng Li;Yizhou Yu - 通讯作者:
Yizhou Yu
Neural Style Transfer: A Review
- DOI:
- 发表时间:
- 期刊:
- 影响因子:
- 作者:
Yongcheng Jing;Yezhou Yang;Zunlei Feng;Jingwen Ye;Yizhou Yu;Mingli Song - 通讯作者:
Mingli Song
Sparse similarity matrix learning for visual object retrieval
用于视觉对象检索的稀疏相似矩阵学习
- DOI:
10.1109/ijcnn.2013.6707063 - 发表时间:
2013 - 期刊:
- 影响因子:0
- 作者:
Zhicheng Yan;Yizhou Yu - 通讯作者:
Yizhou Yu
Real-time data driven deformation with affine bones
- DOI:
10.1007/s00371-010-0474-6 - 发表时间:
2010-04-17 - 期刊:
- 影响因子:2.900
- 作者:
Byung-Uck Kim;Wei-Wei Feng;Yizhou Yu - 通讯作者:
Yizhou Yu
Yizhou Yu的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Yizhou Yu', 18)}}的其他基金
III: Small:Collaborative Research: Coordinated Visualization for Comparative Analysis of Cross-Subject, Multi-Measure, Multi-Dimensional Brain Imaging Data
III:小:协作研究:跨受试者、多测量、多维度脑成像数据比较分析的协调可视化
- 批准号:
0914631 - 财政年份:2009
- 资助金额:
$ 32.5万 - 项目类别:
Standard Grant
相似海外基金
Efficient algorithms for the block relocation and premarshalling problems based on a realistic model
基于现实模型的块重定位和预编组问题的有效算法
- 批准号:
18K04607 - 财政年份:2018
- 资助金额:
$ 32.5万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Collaborative Research: NCS-FO: Learning Efficient Visual Representations From Realistic Environments Across Time Scales
合作研究:NCS-FO:从跨时间尺度的现实环境中学习高效的视觉表示
- 批准号:
1837827 - 财政年份:2017
- 资助金额:
$ 32.5万 - 项目类别:
Standard Grant
Studies on Development of High-Efficient and Reliable Cooling Flow Control Devices under a Realistic Gas Turbine Environment
真实燃气轮机环境下高效可靠冷却流量控制装置的研制研究
- 批准号:
17K06138 - 财政年份:2017
- 资助金额:
$ 32.5万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Efficient and more realistic mechanisms for matching and resource allocation problems
高效、更现实的匹配和资源分配问题机制
- 批准号:
487666-2016 - 财政年份:2016
- 资助金额:
$ 32.5万 - 项目类别:
Postdoctoral Fellowships
Collaborative Research: NCS-FO: Learning Efficient Visual Representations From Realistic Environments Across Time Scales
合作研究:NCS-FO:从跨时间尺度的现实环境中学习高效的视觉表示
- 批准号:
1631403 - 财政年份:2016
- 资助金额:
$ 32.5万 - 项目类别:
Standard Grant
Collaborative Research: NCS-FO: Learning Efficient Visual Representations From Realistic Environments Across Time Scales
合作研究:NCS-FO:从跨时间尺度的现实环境中学习高效的视觉表示
- 批准号:
1631460 - 财政年份:2016
- 资助金额:
$ 32.5万 - 项目类别:
Standard Grant
Efficient numerical investigation of flow control on wind turbine rotors under realistic conditions
实际条件下风力涡轮机转子流动控制的高效数值研究
- 批准号:
218654480 - 财政年份:2012
- 资助金额:
$ 32.5万 - 项目类别:
Research Grants
Efficient and realistic rendering of dynamic scenes with dynamic BRDFs
使用动态 BRDF 高效、真实地渲染动态场景
- 批准号:
21700112 - 财政年份:2009
- 资助金额:
$ 32.5万 - 项目类别:
Grant-in-Aid for Young Scientists (B)
Realistic and efficient illumination and rendering with Light Fields
使用光场实现真实高效的照明和渲染
- 批准号:
155591-1997 - 财政年份:2000
- 资助金额:
$ 32.5万 - 项目类别:
Discovery Grants Program - Individual