DEFORM: Large Scale Shape Analysis of Deformable Models of Humans

DEFORM:人体变形模型的大规模形状分析

基本信息

  • 批准号:
    EP/S010203/1
  • 负责人:
  • 金额:
    $ 172.05万
  • 依托单位:
  • 依托单位国家:
    英国
  • 项目类别:
    Fellowship
  • 财政年份:
    2019
  • 资助国家:
    英国
  • 起止时间:
    2019 至 无数据
  • 项目状态:
    未结题

项目摘要

Recently, computer vision is witnessing a paradigm shift. Standard robust features, such as Scale Invariant Feature Transform (SIFT), Histogram of Oriented Gradienst (HoGs), etc., are replaced by learnable filters via the application of Deep Convolutional Neural Networks (DCNNs). Furthermore, for applications (e.g., detection, tracking, recognition, etc.) that involve deformable objects, such as human bodies/faces/hands etc., traditional statistical or physics-based deformable models are combined with DCNNs with very good results. The current progress is made due to the abundance of complex visual data in the Big Data era, spread mostly through the Internet via web services such as Youtube, Flickr, and Google Images. The latter has led to the development of huge databases (such as ImageNet, Microsoft COCO, and 300W, etc.) consisting of visual data captured "in-the wild". Furthermore, the scientific and industrial community has undertaken large-scale annotation tasks. For example, me and my group have made huge efforts to annotate over 30K facial images and 500K video frames with regards to a large number of facial landmarks. The COCO team has annotated thousands of body images with regards to body joints, etc. All the above annotations generally refer to a set of sparse parts of objects and/or their segments, which can be annotated by humans (e.g., through crowd sourcing). In order to make the next step in automatic understanding of a scene in general, and humans and their actions, in particular, the community needs to acquire 3D dense information. Even though the collection of 2D intensity images is now a relatively easy and inexpensive process, the collection of high-resolution 3D scans of deformable objects, such as humans and their (body) parts, still remains an expensive and laborious process. This is the principal reason why very limited efforts have been made in collecting large-scale databases of 3D faces, heads, hands, bodies, etc.In DEFORM, I propose to perform large-scale collection of high-resolution 4D sequences of humans. Furthermore, I propose new lines of research in order to provide high quality annotations regarding the correspondences between the 2D intensity "in-the-wild" images and the dense 3D structure of deformable objects' shapes and in particular of humans and their parts. Establishing dense 2D-to-3D correspondences can effortlessly solve many image-level tasks such as landmark (part) localisation, dense semantic part segmentation, estimation of deformations (i.e., behaviour), etc.
最近,计算机视觉正在经历一场范式转变。标准的鲁棒特征,例如尺度不变特征变换(SIFT)、定向直方图(HoG)等,通过应用深度卷积神经网络(DCNN),由可学习的滤波器代替。此外,对于应用程序(例如,检测、跟踪、识别等)涉及可变形物体,例如人体/脸/手等,传统的基于统计或物理的可变形模型与DCNN相结合,具有非常好的结果。目前的进展是由于大数据时代丰富的复杂视觉数据,主要通过互联网通过Youtube,Flickr和Google Images等网络服务传播。后者导致了巨大数据库的发展(如ImageNet,Microsoft COCO和300 W等)。由“野外”捕获的视觉数据组成。此外,科学和工业界承担了大规模的注释任务。例如,我和我的团队已经做出了巨大的努力来注释超过30 K的面部图像和500 K的视频帧,这些图像和视频帧涉及大量的面部标志。COCO团队已经注释了数千个关于身体关节等的身体图像。所有上述注释通常是指对象的一组稀疏部分和/或它们的片段,其可以由人类注释(例如,众包(crowd sourcing)。为了在自动理解一般场景,特别是人类及其行为方面迈出下一步,社区需要获取3D密集信息。尽管2D强度图像的收集现在是一个相对容易和便宜的过程,但可变形物体(例如人类及其(身体)部位)的高分辨率3D扫描的收集仍然是一个昂贵和费力的过程。这就是为什么在收集3D面部、头部、手部、身体等的大规模数据库方面所做的努力非常有限的主要原因。在DEFORM中,我建议进行大规模的高分辨率4D人类序列的收集。此外,我提出了新的研究路线,以提供高质量的注释之间的对应关系的2D强度“在野外”的图像和密集的3D结构的可变形物体的形状,特别是人类和他们的部分。建立密集的2D到3D对应关系可以毫不费力地解决许多图像级任务,例如地标(部分)定位、密集语义部分分割、变形估计(即,行为)等。

项目成果

期刊论文数量(10)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation
  • DOI:
    10.1007/s11263-021-01494-4
  • 发表时间:
    2020-12
  • 期刊:
  • 影响因子:
    19.5
  • 作者:
    Mehdi Bahri;Eimear O' Sullivan;Shunwang Gong;Feng Liu;Xiaoming Liu;M. Bronstein;S. Zafeiriou
  • 通讯作者:
    Mehdi Bahri;Eimear O' Sullivan;Shunwang Gong;Feng Liu;Xiaoming Liu;M. Bronstein;S. Zafeiriou
Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes
  • DOI:
    10.1109/iccv51070.2023.01344
  • 发表时间:
    2023-10
  • 期刊:
  • 影响因子:
    0
  • 作者:
    F. Babiloni;Matteo Maggioni;T. Tanay;Jiankang Deng;A. Leonardis;S. Zafeiriou
  • 通讯作者:
    F. Babiloni;Matteo Maggioni;T. Tanay;Jiankang Deng;A. Leonardis;S. Zafeiriou
Inverse Image Frequency for Long-tailed Image Recognition
长尾图像识别的逆图像频率
  • DOI:
    10.48550/arxiv.2209.04861
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Alexandridis K
  • 通讯作者:
    Alexandridis K
Binary Graph Neural Networks
{{ 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 }}

Stefanos Zafeiriou其他文献

Stefanos Zafeiriou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('Stefanos Zafeiriou', 18)}}的其他基金

GNOMON: Deep Generative Models in non-Euclidean Spaces for Computer Vision & Graphics
GNOMON:计算机视觉非欧几里得空间中的深度生成模型
  • 批准号:
    EP/X011364/1
  • 财政年份:
    2023
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Research Grant
Adaptive Facial Deformable Models for Tracking (ADAManT)
用于跟踪的自适应面部变形模型 (ADAManT)
  • 批准号:
    EP/L026813/1
  • 财政年份:
    2014
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Research Grant

相似国自然基金

水稻穗粒数调控关键因子LARGE6的分子遗传网络解析
  • 批准号:
  • 批准年份:
    2022
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
量子自旋液体中拓扑拟粒子的性质:量子蒙特卡罗和新的large-N理论
  • 批准号:
  • 批准年份:
    2020
  • 资助金额:
    62 万元
  • 项目类别:
    面上项目
甘蓝型油菜Large Grain基因调控粒重的分子机制研究
  • 批准号:
    31972875
  • 批准年份:
    2019
  • 资助金额:
    58.0 万元
  • 项目类别:
    面上项目
Large PB/PB小鼠 视网膜新生血管模型的研究
  • 批准号:
    30971650
  • 批准年份:
    2009
  • 资助金额:
    8.0 万元
  • 项目类别:
    面上项目
基因discs large在果蝇卵母细胞的后端定位及其体轴极性形成中的作用机制
  • 批准号:
    30800648
  • 批准年份:
    2008
  • 资助金额:
    20.0 万元
  • 项目类别:
    青年科学基金项目
LARGE基因对口腔癌细胞中α-DG糖基化及表达的分子调控
  • 批准号:
    30772435
  • 批准年份:
    2007
  • 资助金额:
    29.0 万元
  • 项目类别:
    面上项目

相似海外基金

Renewal application: How do ecological trade-offs drive ectomycorrhizal fungal community assembly? Fine- scale processes with large-scale implications
更新应用:生态权衡如何驱动外生菌根真菌群落组装?
  • 批准号:
    MR/Y011503/1
  • 财政年份:
    2025
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Fellowship
LSS_BeyondAverage: Probing cosmic large-scale structure beyond the average
LSS_BeyondAverage:探测超出平均水平的宇宙大尺度结构
  • 批准号:
    EP/Y027906/1
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Research Grant
CSR: Small: Multi-FPGA System for Real-time Fraud Detection with Large-scale Dynamic Graphs
CSR:小型:利用大规模动态图进行实时欺诈检测的多 FPGA 系统
  • 批准号:
    2317251
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Standard Grant
CRII: OAC: A Compressor-Assisted Collective Communication Framework for GPU-Based Large-Scale Deep Learning
CRII:OAC:基于 GPU 的大规模深度学习的压缩器辅助集体通信框架
  • 批准号:
    2348465
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Standard Grant
Collaborative Research: OAC Core: Distributed Graph Learning Cyberinfrastructure for Large-scale Spatiotemporal Prediction
合作研究:OAC Core:用于大规模时空预测的分布式图学习网络基础设施
  • 批准号:
    2403312
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Standard Grant
CAREER: Large scale geometry and negative curvature
职业:大规模几何和负曲率
  • 批准号:
    2340341
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Continuing Grant
Continuous, Large-scale Manufacturing of Functionalized Silver Nanowire Transparent Conducting Films
功能化银纳米线透明导电薄膜的连续大规模制造
  • 批准号:
    2422696
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Standard Grant
CAREER: A Multi-faceted Framework to Enable Computationally Efficient Evaluation and Automatic Design for Large-scale Economics-driven Transmission Planning
职业生涯:一个多方面的框架,可实现大规模经济驱动的输电规划的计算高效评估和自动设计
  • 批准号:
    2339956
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Continuing Grant
CAREER: Strategic Interactions, Learning, and Dynamics in Large-Scale Multi-Agent Systems: Achieving Tractability via Graph Limits
职业:大规模多智能体系统中的战略交互、学习和动态:通过图限制实现可处理性
  • 批准号:
    2340289
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Continuing Grant
Collaborative Research: SHF: Medium: Enabling Graphics Processing Unit Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的图形处理单元性能仿真
  • 批准号:
    2402804
  • 财政年份:
    2024
  • 资助金额:
    $ 172.05万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了