Robust single-view geometry and motion reconstruction

By Hao Li, Bart Adams, Leonidas J. Guibas, Mark Pauly. ACM Transactions on Graphics, 2009

426 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/4dfddd76148db25a92c91322bb403342543938b8

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

1 An End-to-End Framework for Evaluating Surface Reconstruction (2011, methodology): “For instance, surface reconstruction is a crucial first step in the recovery of non-rigid motion of time-varying geometry [Sharf et al. 2008; Li et al. 2009], and used as “ground-truth” data for multi-view stereo reconstruction evaluation [Seitz et al.”
Dense Human Body Correspondences Using Convolutional Networks (2015, methodology): “With the popularization of commodity 3D scanners and recent advances in correspondence algorithms for deformable shapes, human bodies can now be easily digitized [24, 29, 11] and their performances captured using a single RGB-D sensor [23, 42].”
Blending liquids (2014, methodology): “Our work is closely related to the non-rigid ICP algorithms [Am-berg et al. 2007; Li et al. 2009].”
Random Forests for Real Time 3D Face Analysis (2012, methodology): “(2009) was used, together with graph-based non-rigid ICP (Li et al. 2009), to adapt the generic face template to the point cloud.”
Fusion4D (2016, methodology): “Accommodating General Scenes: The approach of [Li et al. 2009] uses a coarse approximation of the scanned object as a shape prior to obtain high quality nonrigid reconstructions of general scenes.”
User-Specific Hand Modeling from Monocular Depth Sequences (2014, background): “Li et al. [15] adapt the general-purpose system [16] to template adaptation and detail enhancement to produce impressive shape recovery given reasonably high-resolution and largely-frontal input sequences.”
Example-based facial rigging (2010, methodology): “In the case of 3D scans, we align the generic rest pose A0 to the input shapes using the non-rigid registration method of [Li et al. 2009].”
Real Time Head Pose Estimation from Consumer Depth Cameras (2011, methodology): “The personalized template is used for accurate rigid tracking. to such personalized template, each subject's sequence of head rotations was tracked using ICP [1], resulting in a pose estimate for each frame.”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “A user turns the head in front of the depth sensor, the scans are integrated into a point cloud model [69] and a generic template is fit to it using graph-based non-rigid ICP [70].”
Automatic acquisition of high-fidelity facial performances using monocular videos (2014, methodology): “One solution to the problem of marker-less facial capture is the use of depth and/or color data obtained from structured light systems [Zhang et al. 2004; Ma et al. 2008; Li et al. 2009; Weise et al. 2009].”
Realtime facial animation with on-the-fly correctives (2013, methodology): “Correspondences are computed using variants of non-rigid registration and texture tracking [Zhang et al. 2004; Li et al. 2009; Fu-rukawa and Ponce 2009; Bradley et al. 2010; Beeler et al. 2011] or more recently with a joint optimization between capture and tracking [Valgaerts et al. 2012].”
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors (2021, methodology): “Given a prescanned template, [22, 59, 15] track dense surface deformations from single-view RGB input [17, 18].”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, background): “When features of two points (or clusters) match, a meaningful correspondence may exist.”
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (2023, positive): “Following dynamic fusion works [4, 17, 32], we employ LBS [44] to compute the warped Gaussian µ tj and q tj as Eq.”