Comprehensive Human Performance Capture from Monocular Video Footage

从单眼视频片段中捕捉全面的人类表现

• 批准号: 265624298
• 负责人: Professor Dr.-Ing. Marcus Magnor
• 金额: --
• 依托单位: Institut für Informationsverarbeitung
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2015
• 资助国家: 德国
• 起止时间: 2014-12-31 至 2020-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/265624298?language=en
• 关键词: Comprehensive; Human; Performance; Capture; Monocular

Goal of the proposed research is to comprehensively, photo-realistically model human performances from conventional, monocular video footage. We plan to devise methods to estimate the geometry, pose, motion, illumination as well as texture and reflectance characteristics of a person from a single video sequence. Furthermore, we will develop algorithms to augment texture details, to edit pose and motion, and to convincingly render the model into novel scenes. We intend to employ model- as well as example-based approaches from Computer Vision in conjunction with interactive correction, augmentation, and error-concealing rendering methods from Computer Graphics. Our joint research shall make contributions to the general challenge of underconstrained reconstruction for photo-realistic modeling and rendering. The project intends to lay the methodical foundations for creating digital doubles of actors based on nothing more than their movies, enabling digital conservation of even already deceased actors.

拟议的研究的目标是对传统，单眼录像带的人类表演进行全面的，真实的现实方式。我们计划设计方法来估计从单个视频序列中的人的几何形状，姿势，运动，照明以及纹理和反射特征。此外，我们将开发算法以增强纹理细节，编辑姿势和运动，并令人信服地将模型呈现为新颖的场景。我们打算采用来自计算机视觉的模型以及基于示例的方法，并结合交互式校正，增强和来自计算机图形的渲染方法。我们的联合研究应为光真逼真的建模和渲染的不受限制重建的一般挑战做出贡献。该项目打算为创建数字双打演员的基础，基于他们的电影而创建数字双打演员，从而使数字保护甚至已经去世了。

项目成果

RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation

• DOI: 10.1109/cvpr.2019.00797
• 发表时间: 2019-02
• 期刊: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Bastian Wandt;B. Rosenhahn

A Kinematic Chain Space for Monocular Motion Capture

• DOI: 10.1007/978-3-030-11018-5_4
• 发表时间: 2017-02
• 期刊: ArXiv
• 作者: Bastian Wandt;H. Ackermann;B. Rosenhahn

Detailed Human Avatars from Monocular Video

• DOI: 10.1109/3dv.2018.00022
• 发表时间: 2018-08
• 期刊: 2018 International Conference on 3D Vision (3DV)
• 作者: Thiemo Alldieck;M. Magnor;Weipeng Xu;C. Theobalt;Gerard Pons-Moll

Learning to Reconstruct People in Clothing From a Single RGB Camera

• DOI: 10.1109/cvpr.2019.00127
• 发表时间: 2019-03
• 期刊: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Thiemo Alldieck;M. Magnor;Bharat Lal Bhatnagar;C. Theobalt;Gerard Pons-Moll

Video Based Reconstruction of 3D People Models

• DOI: 10.1109/cvpr.2018.00875
• 发表时间: 2018-03
• 期刊: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
• 作者: Thiemo Alldieck;M. Magnor;Weipeng Xu;C. Theobalt;Gerard Pons-Moll