CAREER: Physics-Based Differentiable and Inverse Rendering

职业:基于物理的可微分和逆向渲染

基本信息

  • 批准号:
    2239627
  • 负责人:
  • 金额:
    $ 60万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2023
  • 资助国家:
    美国
  • 起止时间:
    2023-09-01 至 2028-08-31
  • 项目状态:
    未结题

项目摘要

This project will develop new computational tools to infer physical parameters such as object shape and optical properties of a scene from measured images such as photographs. These tools are essential for building digital twins of real-world objects and will enable new applications in a wide array of fields including computer vision, computational imaging, robotics, and virtual/augmented reality (VR/AR). Unlike many existing methods that are purely data-driven, this research will develop inference techniques that leverage a simulator of how light propagates. This simulator will be differentiable, meaning that it is possible to smoothly relate its control parameters to its decisions, offering a new level of generality and physical accuracy for recovering parameters reliably under complex scenarios such as illumination from reflected light. Project outcomes have the potential for broad impact by creating new areas in computer graphics and computational photonics. Additional broad impact will derive from the PI's commitment to promoting STEM education for underrepresented minorities, and from the project facilitating UCI’s outreach programs at the undergraduate and high school levels including lab visits to allow hands-on experience with software development. This research will enable differentiable and inverse rendering that is efficient, physically accurate, and sufficiently general to handle arbitrary scene parameters under a wide variety of light transport phenomena. The work will make the following four core contributions: first, devising new mathematical tools to describe how infinitesimal changes in a virtual scene affect the distribution of light, supporting a variety of light transport models including steady state, polarized, and transient; second, introducing physics-based differentiable rendering algorithms that enjoy the generality of the new formulations while providing low-variance derivative estimates; third, leveraging these algorithms to build differentiable rendering software systems capable of efficiently handling complex real-world configurations; and, lastly, utilizing the new algorithms and systems to introduce physics-based inverse rendering pipelines that offer a new level of generality and accuracy benefiting a wide array of applications.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
该项目将开发新的计算工具,从照片等测量图像中推断物体形状和场景的光学性质等物理参数。这些工具对于构建真实世界对象的数字孪生兄弟至关重要,并将在包括计算机视觉、计算成像、机器人和虚拟/增强现实(VR/AR)在内的广泛领域实现新的应用。与许多纯粹由数据驱动的现有方法不同,这项研究将开发利用光如何传播的模拟器的推理技术。该模拟器将是可区分的,这意味着它可以平稳地将其控制参数与其决策联系起来,为在复杂场景下可靠地恢复参数提供了新的通用性和物理精度,例如来自反射光的照明。通过在计算机图形学和计算光子学领域创造新的领域,项目成果有可能产生广泛的影响。其他广泛的影响将来自于国际和平协会致力于促进代表不足的少数族裔的STEM教育,以及促进UCI在本科和高中层面的外联计划,包括参观实验室,以便获得软件开发的实践经验。这项研究将使可微和逆渲染成为可能,这种渲染高效、物理准确,并且足够通用,可以处理各种光传输现象下的任意场景参数。这项工作将做出以下四个核心贡献:第一,设计新的数学工具来描述虚拟场景中的微小变化如何影响光的分布,支持包括稳态、偏振和瞬变在内的各种光传输模型;第二,引入基于物理的可微绘制算法,在提供低方差导数估计的同时享受新公式的一般性;第三,利用这些算法来构建能够有效地处理复杂现实世界配置的可微绘制软件系统;最后,利用新的算法和系统引入基于物理的反向渲染管道,提供更高水平的通用性和准确性,使广泛的应用受益。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。

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 }}

Shuang Zhao其他文献

Holocene aeolian dust accumulation rates across the Chinese Loess Plateau
中国黄土高原全新世风沙堆积率
  • DOI:
    10.1016/j.gloplacha.2021.103720
  • 发表时间:
    2021-12
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Shuang Zhao;Dunsheng Xia;Kexin Lü
  • 通讯作者:
    Kexin Lü
Coagulation performance and membrane fouling of polyferric chloride/epichlorohydrin–dimethylamine in coagulation/ultrafiltration combined process
混凝/超滤联合工艺中聚合氯化铁/环氧氯丙烷·二甲胺的混凝性能及膜污染
  • DOI:
  • 发表时间:
    2015
  • 期刊:
  • 影响因子:
    15.1
  • 作者:
    Lijuan Feng;Wenyu Wang;Ruiqi Feng;Shuang Zhao;Hongyu Dong;Shenglei Sun;Baoyu Gao;Qinyan Yue
  • 通讯作者:
    Qinyan Yue
Influence of geomorphology and leaching on the formation of Permian bauxite in northern Guizhou Province, South China
地貌及淋滤对黔北二叠系铝土矿形成的影响
  • DOI:
    10.1016/j.gexplo.2019.106446
  • 发表时间:
    2020-03
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Peigang Li;Wenchao Yu;Yuansheng Du;Xulong Lai;Shenfu Weng;Dawei Pang;Guolin Xiong;Zhiyuan Lei;Shuang Zhao;Shiqiang Yang
  • 通讯作者:
    Shiqiang Yang
Multilayered construction of glucose oxidase and gold nanoparticles on Au electrodes based on layer-by-layer covalent attachment
基于逐层共价连接的葡萄糖氧化酶和金纳米粒子在金电极上的多层结构
  • DOI:
    10.1016/j.elecom.2005.11.014
  • 发表时间:
    2006-04
  • 期刊:
  • 影响因子:
    5.4
  • 作者:
    Weiwei Yang;Jinxing Wang;Shuang Zhao;Yingying Sun;Changqing Sun*
  • 通讯作者:
    Changqing Sun*
Preparation of Si3N4 ceramic foams by simultaneously using egg white protein and fish collagen
蛋清蛋白和鱼胶原蛋白同时制备氮化硅陶瓷泡沫
  • DOI:
    10.1016/j.ceramint.2012.06.046
  • 发表时间:
    2013
  • 期刊:
  • 影响因子:
    5.2
  • 作者:
    Liu-yan Yin;Xin-gui Zhou;Jin-shan Yu;Hong-lei Wang;Shuang Zhao;Zheng Luo;Bei Yang
  • 通讯作者:
    Bei Yang

Shuang Zhao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('Shuang Zhao', 18)}}的其他基金

CHS: Medium: Collaborative Research: Physics and Learning Integration Using Differentiable Rendering
CHS:媒介:协作研究:使用可微渲染的物理和学习集成
  • 批准号:
    1900927
  • 财政年份:
    2019
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CHS: Small: Predictive Material Appearance Modeling at Multiple Scales
CHS:小型:多尺度预测材料外观建模
  • 批准号:
    1813553
  • 财政年份:
    2018
  • 资助金额:
    $ 60万
  • 项目类别:
    Standard Grant

相似国自然基金

Understanding complicated gravitational physics by simple two-shell systems
  • 批准号:
    12005059
  • 批准年份:
    2020
  • 资助金额:
    24.0 万元
  • 项目类别:
    青年科学基金项目
Chinese Physics B
  • 批准号:
    11224806
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Science China-Physics, Mechanics & Astronomy
  • 批准号:
    11224804
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Frontiers of Physics 出版资助
  • 批准号:
    11224805
  • 批准年份:
    2012
  • 资助金额:
    20.0 万元
  • 项目类别:
    专项基金项目
Chinese physics B
  • 批准号:
    11024806
  • 批准年份:
    2010
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目

相似海外基金

CAREER: An Integrated Framework for Resilience Analytics: From Physics-based Modeling of Building Components to Dynamics of Community Level Recovery
职业:弹性分析的综合框架:从基于物理的建筑组件建模到社区层面恢复的动态
  • 批准号:
    2347722
  • 财政年份:
    2023
  • 资助金额:
    $ 60万
  • 项目类别:
    Standard Grant
CAREER: Combining Machine Learning and Physics-based Modeling Approaches for Accelerating Scientific Discovery
职业:结合机器学习和基于物理的建模方法来加速科学发现
  • 批准号:
    2239175
  • 财政年份:
    2023
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CAREER: Continuous Flow Chemistry of Microelectronics Polymers via Combined Physics-based and Machine Learning Models
职业:通过基于物理和机器学习相结合的微电子聚合物的连续流动化学
  • 批准号:
    2238147
  • 财政年份:
    2023
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CAREER: Using Physics-Based Machine Learning to Reconcile the Crack Tip with the Plastic Zone during Fracture of Metals
职业:使用基于物理的机器学习来协调金属断裂过程中的裂纹尖端与塑性区
  • 批准号:
    2237039
  • 财政年份:
    2023
  • 资助金额:
    $ 60万
  • 项目类别:
    Standard Grant
CAREER: Transforming Biosensor Reliability using Sensor Time-series Data and Physics-based Machine Learning
职业:使用传感器时间序列数据和基于物理的机器学习改变生物传感器的可靠性
  • 批准号:
    2144310
  • 财政年份:
    2022
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CAREER: Synergistic physics-based and deep learning cardiovascular flow modeling
职业:基于协同物理和深度学习的心血管血流建模
  • 批准号:
    2247173
  • 财政年份:
    2022
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CAREER: Synergistic physics-based and deep learning cardiovascular flow modeling
职业:基于协同物理和深度学习的心血管血流建模
  • 批准号:
    2143249
  • 财政年份:
    2022
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CAREER: Automated physics-based distillation of coherent structures and mechanisms in unsteady and turbulent flows
职业:基于物理的自动蒸馏非定常和湍流中的相干结构和机制
  • 批准号:
    2238770
  • 财政年份:
    2022
  • 资助金额:
    $ 60万
  • 项目类别:
    Continuing Grant
CAREER: MaLPhySiCS - Machine Learning-assisted Physics-based Simulation and Control of Soft robots
职业:MaLPhySiCS - 机器学习辅助的基于物理的软机器人仿真和控制
  • 批准号:
    2047663
  • 财政年份:
    2021
  • 资助金额:
    $ 60万
  • 项目类别:
    Standard Grant
CAREER: An Integrated Framework for Resilience Analytics: From Physics-based Modeling of Building Components to Dynamics of Community Level Recovery
职业:弹性分析的综合框架:从基于物理的建筑组件建模到社区层面恢复的动态
  • 批准号:
    2047832
  • 财政年份:
    2021
  • 资助金额:
    $ 60万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了