Free-viewpoint video of human actors

By Joel Carranza, Christian Theobalt, Marcus A. Magnor, Hans-Peter Seidel. ACM Transactions on Graphics, 2003

761 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/89a7dd58e31b4ea69f59351fef7dfd4fa1cc6273

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey (2008, methodology): “Background modeling is often used in different applications to model the background and then detect the moving objects in the scene like in video surveillance [2, 3], optical motion capture [4, 5-6] and multimedia [7, 8-10].”
Articulated mesh animation from multi-view silhouettes (2008, background): “Articulated templates are often used to improve pose tracking, but they do not deform to capture details in the video [Carranza et al. 2003; Theobalt et al. 2007; Cheung et al. 2005; Anguelov et al. 2005; Corazza et al. 2006; Balan et al. 2007].”
Space-time Neural Irradiance Fields for Free-Viewpoint Video (2020, methodology): “Several methods can reduce the required number of input views by focusing on specific domains such as performance capture [8, 14, 21] and video re-animation [29, 34, 35, 62, 9].”
AutoInt: Automatic Integration for Fast Neural Volume Rendering (2020, background): “Image-based rendering and novel view synthesis are fundamental problems in computer vision and graphics (e.g., [5, 56]).”
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living (2012, neutral): “skeletons and stick figures [19], etc.”
Free-Viewpoint Video of Human Actors Using Multiple Handheld Kinects (2013, background): “The first is the spatial vertex coloring using texture information from only the three RGB images of the current frame [55], [58].”
Traditional and recent approaches in background modeling for foreground detection: An overview (2014, background): “Many applications in this research area (video surveillance [56][263][221], optical motion capture [15], multimedia application [48]) need in the first step to detect the moving objects in the scene.”
Multiview Imaging and 3DTV (2007, methodology): “One model-based FTV method that is suitable for synchronized multiview video footage consists of matching model to object silhouettes based on an analysis-by-synthesis approach [28], as shown in Figure 5.”
HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video (2022, methodology): “This problem – free-viwepoint rendering of a moving subject – is a longstanding research challenge, as it involves synthesizing previously unseen camera views while accounting for cloth folds, hair movement, and complex body poses [5, 6, 15, 18, 27, 38, 59, 65].”
Multi-Garment Net: Learning to Dress 3D People From Images (2019, background): “The classical approach to bring dynamic sequences into correspondence is to deform meshes non-rigidly [11, 18, 10] or volumetric shape representations [28, 2] to fit multiple image silhouettes.”
Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans (2020, background): “To capture human models in the highly sparse multi-view setting, template-based methods [4, 10, 16, 54] assume that there are pre-scanned human models.”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, methodology): “Top-down, free-form methods non-rigidly deform meshes [14, 22, 12] or volumetric shape representations [36, 4].”
Recent Advanced Statistical Background Modeling for Foreground Detection - A Systematic Survey (2011, background): “Different applications such as video surveillance [1], optical motion capture [2-4] and multimedia [5-7] n eed firstly to model the background and then to detect the moving objects.”
Jump (2016, background): “A second format that allows for 3D translation of the viewer is free viewpoint video [Carranza et al. 2003; Collet et al. 2015; Zitnick et al. 2004; Smolic 2011], which allows the viewer to move freely within some volume.”
Dynamic View Synthesis from Dynamic Monocular Video (2021, methodology): “, humans) [8, 12, 19] or transitions between input views only [3].”
The Tactile Internet: Applications and Challenges (2014, methodology): “Digital image processing of video information can be used to synthetically render the viewpoint of the viewer to another spot, named free-viewpoint video [15].”
Vision-based human motion analysis: An overview (2007, background): “Alternatively, these parameters can be recovered in an initialization step, where the observed person is to adopt a speciﬁed pose [15,6].”