Corpus ID: 202541221

Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity

  title={Intrinsic Dynamic Shape Prior for Fast, Sequential and Dense Non-Rigid Structure from Motion with Detection of Temporally-Disjoint Rigidity},
  author={Vladislav Golyanik and Andr{\'e} Jonas and Didier Stricker and Christian Theobalt},
While dense non-rigid structure from motion (NRSfM) has been extensively studied from the perspective of the reconstructability problem over the recent years, almost no attempts have been undertaken to bring it into the practical realm. The reasons for the slow dissemination are the severe ill-posedness, high sensitivity to motion and deformation cues and the difficulty to obtain reliable point tracks in the vast majority of practical scenarios. To fill this gap, we propose a hybrid approach… Expand
Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints
This work introduces the first dense neural non-rigid structure from motion (N-NRSfM) approach, which can be trained end-to-end in an unsupervised manner from 2D point tracks and enables multiple applications including shape compression, completion and interpolation, among others. Expand
Dense Non-Rigid Structure from Motion: A Manifold Viewpoint
This paper proposes algorithms that can overcome limitations with the previous methods and, at the same time, can recover a reliable dense 3D structure of a non-rigid object with higher accuracy and significantly improves accuracy, scalability, and robustness against noise. Expand


A scalable, efficient, and accurate solution to non-rigid structure from motion
This paper proposes incorporating existing point trajectory low-rank models into a probabilistic framework for matrix normal distributions, and shows that formulating the problem in terms of distributions over trajectories brings remarkable improvements, especially in generality and efficiency. Expand
Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
This paper proposes a new approach for dense NRSfM by modeling the problem on a Grassmann manifold that is scalable and more accurate than state-of-the-art methods, and more robust to noise and generalizes to highly nonlinear deformations. Expand
Dense non-rigid structure-from-motion made easy — A spatial-temporal smoothness based solution
Experimental results show that the proposed spatial-temporal smoothness based method for solving dense non-rigid structure-frommotion (NRSfM) outperforms state-of-the-art denseNonrigid reconstruction methods. Expand
Online Dense Non-Rigid 3D Shape and Camera Motion Recovery
A sequential solution to dense non-rigid structure from motion that recovers the camera motion and 3D shape of non- Rigid objects by processing a monocular image sequence as the data arrives is described. Expand
Implicit Non-Rigid Structure-from-Motion with Priors
  • S. Olsen, A. Bartoli
  • Computer Science, Mathematics
  • Journal of Mathematical Imaging and Vision
  • 2007
An algorithm for achieving a Maximum A Posteriori (map) solution is proposed and it is shown experimentally that the map-solution generalizes far better than the prior-free Maximum Likelihood (ml) solution. Expand
Structure from Recurrent Motion: From Rigidity to Recurrency
This paper proposes a new method from a long monocular video sequence observing a non-rigid object performing recurrent and possibly repetitive dynamic action to reduce NRSfM problems to rigid ones provided that certain recurrency condition is satisfied. Expand
Sequential Non-Rigid Structure-from-Motion with the 3D-Implicit Low-Rank Shape Model
This paper proposes an incremental approach to the estimation of deformable models and depart from the traditional explicit low-rank shape model and proposes a variant that it results in a simpler formulation of the motion matrix and provides the ability to represent degenerate deformation modes. Expand
Spatio-temporal union of subspaces for multi-body non-rigid structure-from-motion
This paper proposes a unified framework to jointly segment and reconstruct multiple non-rigid objects and proposes to exploit the structure of the scenes along both temporal direction and spatial direction, thus achieving a spatio-temporal representation. Expand
Dense Batch Non-Rigid Structure from Motion in a Second
The modification results in an efficient single-core CPU implementation enabling dense factorisations of long image sequences with tens of thousands of points into camera pose and non-rigid shape in seconds, i.e., at least two orders of magnitude faster than the runtimes reported in the literature so far. Expand
Computing Smooth Time Trajectories for Camera and Deformable Shape in Structure from Motion with Occlusion
The classical computer vision problems of rigid and nonrigid structure from motion (SFM) with occlusion are addressed and a novel 3D shape trajectory approach is proposed that solves for the deformable structure as the smooth time trajectory of a single point in a linear shape space. Expand