Mathematically-Guaranteed Global Solutions to Structure-from-Motion

数学保证的运动结构全局解决方案

基本信息

  • 批准号:
    2152766
  • 负责人:
  • 金额:
    $ 30万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2022
  • 资助国家:
    美国
  • 起止时间:
    2022-08-01 至 2025-07-31
  • 项目状态:
    未结题

项目摘要

The central problem of structure from motion (SfM) asks to recover the three-dimensional structure of a scene from projective two-dimensional images. Its study has led to successful commercial applications that impact our society, such as in self-driving cars, robotics, augmented/virtual reality and visual-inertial navigation. Despite the impressive progress in SfM, there are many open computational and mathematical problems. The goal of this project is to address these problems. Not only are these problems important to computer vision research, but they are also fundamental for computational mathematics and optimization research. In particular, mathematically guaranteed global procedures, which avoid unnecessary heuristics and parameters, are expected to be relevant to other applied problems. The overall project aims to create theoretically-guaranteed optimization components for the SfM pipeline. The current pipeline still uses incremental and heuristic procedures, lacks sufficient guarantees for handling highly corrupted datasets and is slow. The specific subprojects are guided by rigorous mathematical approaches. In particular, mathematical arguments suggest optimal choices and definitions. They are also helpful with many practical considerations of SfM, such as reducing the number of parameters and improving robustness to corruption. These arguments are expected to develop into interesting mathematical theorems. The investigator will continue guiding graduate and undergraduate students in research. The investigator will also continue facilitating educational activities that prepare students for successful careers in industry. In particular, arranging summer internships and organizing the industrial problem seminar.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.
运动恢复结构(SfM)的核心问题是从投影的二维图像中恢复场景的三维结构。它的研究导致了影响我们社会的成功商业应用,例如自动驾驶汽车,机器人,增强/虚拟现实和视觉惯性导航。尽管SfM取得了令人印象深刻的进展,但仍有许多开放的计算和数学问题。这个项目的目标就是解决这些问题。这些问题不仅对计算机视觉研究很重要,而且也是计算数学和优化研究的基础。特别是,数学上保证的全球程序,避免不必要的mathematics和参数,预计将相关的其他应用问题。整个项目旨在为SfM管道创建理论上有保证的优化组件。目前的管道仍然使用增量和启发式程序,缺乏足够的保证来处理高度损坏的数据集,并且速度很慢。具体的子项目由严格的数学方法指导。特别是,数学论证提出了最佳选择和定义。它们也有助于SfM的许多实际考虑,例如减少参数的数量和提高对腐败的鲁棒性。这些论点有望发展成有趣的数学定理。研究人员将继续指导研究生和本科生的研究。调查员还将继续促进教育活动,为学生在行业中的成功职业做好准备。特别是安排暑期实习和组织工业问题研讨会。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值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(1)
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 }}

Gilad Lerman其他文献

Estimation of Camera Locations in Highly Corrupted Scenarios: All About that Base, No Shape Trouble
高度损坏场景中摄像机位置的估计:一切都围绕该底座,没有形状问题
Phase transition in random tensors with multiple spikes
具有多个尖峰的随机张量的相变
  • DOI:
  • 发表时间:
    2018
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Wei;Madeline Handschy;Gilad Lerman
  • 通讯作者:
    Gilad Lerman
$${l_p}$$ -Recovery of the Most Significant Subspace Among Multiple Subspaces with Outliers
  • DOI:
    10.1007/s00365-014-9242-6
  • 发表时间:
    2014-07-03
  • 期刊:
  • 影响因子:
    1.200
  • 作者:
    Gilad Lerman;Teng Zhang
  • 通讯作者:
    Teng Zhang
Analysis and algorithms for emℓ/emsubemp/em/sub-based semi-supervised learning on graphs
基于 emℓ/emsubemp/em/sub 的图上半监督学习的分析与算法
Topological Data Analysis and Machine Learning Theory
拓扑数据分析和机器学习理论
  • DOI:
  • 发表时间:
    2012
  • 期刊:
  • 影响因子:
    0
  • 作者:
    G. Carlsson;Rick Jardine;Dmitry Feichtner;D. Morozov;D. Attali;A. Bak;M. Belkin;Peter Bubenik;Brittany Terese Fasy;Jesse Johnson;Matthew Kahle;Gilad Lerman;Sayan Mukherjee;Monica Nicolau;A. Patel;Yusu Wang
  • 通讯作者:
    Yusu Wang

Gilad Lerman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('Gilad Lerman', 18)}}的其他基金

ATD: Robustness, Privacy, and Fairness in Threat Detection
ATD:威胁检测中的稳健性、隐私性和公平性
  • 批准号:
    2124913
  • 财政年份:
    2021
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
ATD: Threat Detection Problems in Precision Agriculture and Satellite Imaging
ATD:精准农业和卫星成像中的威胁检测问题
  • 批准号:
    1830418
  • 财政年份:
    2018
  • 资助金额:
    $ 30万
  • 项目类别:
    Continuing Grant
Theory-Driven Solutions to Robust and Non-Convex Data Science Problems
稳健和非凸数据科学问题的理论驱动解决方案
  • 批准号:
    1821266
  • 财政年份:
    2018
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Novel Paradigms in Geometric Modeling of Large and High-Dimensional Data Sets
大型高维数据集几何建模的新范式
  • 批准号:
    1418386
  • 财政年份:
    2014
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
CAREER: New Paradigms in Geometric Analysis of Data Sets and their Applications
职业:数据集几何分析的新范式及其应用
  • 批准号:
    0956072
  • 财政年份:
    2010
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Collaborative Research: Multi-manifold data modeling: theory, algorithms and applications
协作研究:多流形数据建模:理论、算法和应用
  • 批准号:
    0915064
  • 财政年份:
    2009
  • 资助金额:
    $ 30万
  • 项目类别:
    Continuing Grant
Computational Methods for Exploring the Geometry of Large Data Sets
探索大数据集几何的计算方法
  • 批准号:
    0612608
  • 财政年份:
    2006
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant

相似海外基金

Collaborative Research: SLES: Guaranteed Tubes for Safe Learning across Autonomy Architectures
合作研究:SLES:跨自治架构安全学习的保证管
  • 批准号:
    2331878
  • 财政年份:
    2024
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Collaborative Research: SLES: Guaranteed Tubes for Safe Learning across Autonomy Architectures
合作研究:SLES:跨自治架构安全学习的保证管
  • 批准号:
    2331879
  • 财政年份:
    2024
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Learning Coordination for Multi-Autonomous Multi-Human (MAMH) Agent Systems with Guaranteed Safety
具有安全保证的多自主多人(MAMH)代理系统的学习协调
  • 批准号:
    2332210
  • 财政年份:
    2024
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Local Differential Privacy Technology with Guaranteed Transparency
本地差分隐私技术,保证透明度
  • 批准号:
    23K11110
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
NOVEL DECOMPOSITION ALGORITHMS FOR GUARANTEED GLOBAL OPTIMIZATION OF LARGE-SCALE NONCONVEX STOCHASTIC PROGRAMS
确保大规模非凸随机程序全局优化的新颖分解算法
  • 批准号:
    2232588
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Unravel machine learning blackboxes -- A general, effective and performance-guaranteed statistical framework for complex and irregular inference problems in data science
揭开机器学习黑匣子——针对数据科学中复杂和不规则推理问题的通用、有效和性能有保证的统计框架
  • 批准号:
    2311064
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Development of Data-Collection Algorithms and Data-Driven Control Methods for Guaranteed Stabilization of Nonlinear Systems with Uncertain Equilibria and Orbits
开发数据收集算法和数据驱动控制方法,以保证具有不确定平衡和轨道的非线性系统的稳定性
  • 批准号:
    23K03913
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Fusing a future from Glasgow’s proud heritage: Schedule Guaranteed High-Integrity Structures for a Secure, Safe and Resilient Transition to Net Zero
融合格拉斯哥引以为傲的传统的未来:时间表保证的高完整性结构,以安全、安全和有弹性地过渡到净零
  • 批准号:
    10054861
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Collaborative R&D
Exploring Cosmic Noon and Cosmic Dawn with JWST Guaranteed Time Observations
利用 JWST 保证时间观测探索宇宙正午和宇宙黎明
  • 批准号:
    RGPIN-2020-06023
  • 财政年份:
    2022
  • 资助金额:
    $ 30万
  • 项目类别:
    Discovery Grants Program - Individual
SHF: Small: A Distributed Scalable End-to-End Tail Latency SLO Guaranteed Resource Management Framework for Microservices
SHF:Small:分布式可扩展端到端尾部延迟 SLO 保证的微服务资源管理框架
  • 批准号:
    2226117
  • 财政年份:
    2022
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了