High-quality streamable free-viewpoint video

By Alvaro Collet, Ming Chuang, Pat Sweeney, D. Gillett, D. Evseev, D. Calabrese, Hugues Hoppe, Adam G. Kirk, Steve Sullivan. ACM Transactions on Graphics, 2015

675 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/d468062762decb2470e2840d4bffcd323e599812

How researchers see this paper

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

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (2023, neutral): “Classic methods in this area include [19, 21, 39, 40, 49–51, 98, 104].”
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction (2020, background): “Extremely high-quality reconstruction results have also been demonstrated with tens or even hundreds of cameras [24].”
Deep Volumetric Video From Very Sparse Multi-view Performance Capture (2018, background): “High-end capture solutions use a large number of cameras and active projections [1–3] or controlled lighting conditions [4, 5], and are restricted to professional studio settings.”
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors (2021, methodology): “In particular, the methods by [8] and [14] first perform multi-view stereo for the point cloud generation, followed by mesh construction, simplification, tracking, and post-processing steps such as UV mapping.”
HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video (2022, background): “Col-let et al. [11] and Guo et al. [18] build a system as well as pipeline that produces high-quality streamable [11] or even relightable [18] free-viewpoint videos of moving people.”
Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies (2021, methodology): “First, high-quality human reconstruction generally relies on complicated hardware, such as a dense array of cameras [56, 16] or depth sensors [10, 14].”
Video Based Reconstruction of 3D People Models (2018, methodology): “One way to make fusion and tracking more robust is by using multiple kinects [21, 47] or multi-view [63, 38, 16]; such methods achieve impressive reconstructions but do not register all”
Fusion4D (2016, methodology): “11) we plot the error over the input mesh for our method and [Collet et al. 2015], which shows that our algorithm can match the motion and ﬁne scale details exhibited in this sequence.”
Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video (2020, background): “Free viewpoint rendering is a well-studied problem due to its wide range of applications in movies and virtual/augmented reality [76, 9, 48].”
ClothCap (2017, background): “Other works also use a free-form surface (Collet et al. 2015; Innmann et al. 2016; Newcombe et al. 2015; Wang et al. 2016) but can not separate the clothing from the person and can not retarget it.”
Multi-Garment Net: Learning to Dress 3D People From Images (2019, background): “Although flexible, these require multiview [57, 37, 14], one or more depth cameras [19, 45], or require the subject to stand still while turning the cameras around them [53, 38, 63, 16].”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, neutral): “Common ways to add robustness are pre-scanning the template [88], or using multiple kinects [26, 54] or multiview [67, 44, 19].”
Space-time Neural Irradiance Fields for Free-Viewpoint Video (2020, methodology): “Consequently, most of the existing methods typical require laborious multi-camera setup [78, 11, 52, 13, 6], special hardware [1], or synchronous video captures from multiple viewpoints [3, 4].”
Dynamic FAUST: Registering Human Bodies in Motion (2017, methodology): “There exist previous datasets for 4D registration [21, 39, 45].”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, methodology): “State-of-the-art real-time [11, 10] and extremely highquality [8] reconstruction results have also been demonstrated with tens or even hundreds of cameras using binocular [12] or multiview stereo matching [13] algorithms.”