A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization

By Yuchao Dai, Hongdong Li, Mingyi He. International Journal of Computer Vision, 2012

369 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/74d3e177876b62aeb592a2108ce432c21ac7910a

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 Vision and Pattern Recognition

Citations in the corpus

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding (2018, neutral): “d are effective and efﬁcient in many cases. When there are dynamic motions inside a monocular video, usually there is scale-confusion for each non-rigid movement, thus regularization through low-rank [20], orthographic camera [21], rigidity [22] or ﬁxed number of moving objects [23] are necessary in”
Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model Using Deep Non-Rigid Structure From Motion (2019, methodology): “NRSfM, developed originally to establish a 3D model of a deformable object by observing its motion [4], was developed to solve increasingly accurately the underlying mathematical optimization problems [43, 30, 1, 9], extending to dense reconstruction [11], lifting object cat-”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “Following these results, Dai et al. [27] tried to remove any additional constraints for nonrigid reconstruction (e.g., information about the non-rigid scene, nonrigid shape basis, the coefficients, the deformations, the shapes, etc.) by proposing a prior-free method using low-rank constraints only.”
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video (2015, methodology): “In other words, NRSFM is very difﬁcult to compute with slow camera motion.”
Total Moving Face Reconstruction (2014, background): “, Morphable models [9, 10, 41], AAMs [22, 19], and Nonrigid Sfm [14, 13, 23, 20].”
C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion (2019, methodology): “There are several solutions to the NR-SFM problem which can recover the viewpoint and 3D shape of a deforming object from 2D keypoints across multiple frames [4, 6, 5, 9], the majority of which are based on Bregler’s factorization framework [6].”
Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video (2013, methodology): “[12], in this paper we adopt a trace norm minimization approach to estimate low-rank non-rigid shapes.”