Filters








18,614 Hits in 3.4 sec

Temporally Coherent General Dynamic Scene Reconstruction

Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2020 International Journal of Computer Vision  
Contributions of the work are: an automatic method for initial coarse reconstruction to initialize joint estimation; sparse-to-dense temporal correspondence integrated with joint multi-view segmentation  ...  such as free-view rendering and virtual reality.  ...  If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly  ... 
doi:10.1007/s11263-020-01367-2 fatcat:k4a6n2l4hbfvdo6pp3gczrfhsq

VolumeDeform: Real-time Volumetric Non-rigid Reconstruction [article]

Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger
2016 arXiv   pre-print
Motion tracking is based on a set of extracted sparse color features in combination with a dense depth-based constraint formulation.  ...  We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates.  ...  Sparse Feature Alignment: In addition to the dense depth correspondence association, we use the set of S sparse color-based SIFT matches (see Sec. 5) as constraints in the optimization.  ... 
arXiv:1603.08161v2 fatcat:sksadhn6rrdyhcvq2ve4osx2d4

Temporally Coherent General Dynamic Scene Reconstruction [article]

Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2020 arXiv   pre-print
Contributions of the work are: An automatic method for initial coarse reconstruction to initialize joint estimation; Sparse-to-dense temporal correspondence integrated with joint multi-view segmentation  ...  This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to free-viewpoint  ...  Further results can be found in the supplementary material.  ... 
arXiv:1907.08195v2 fatcat:pcjsowtlj5ejdpnidxerof2kcy

VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction [chapter]

Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger
2016 Lecture Notes in Computer Science  
Motion tracking is based on a set of extracted sparse color features in combination with a dense depth constraint.  ...  We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates.  ...  Sparse Feature Alignment: In addition to the dense depth correspondence association, we use the set of S sparse color-based SIFT matches (see Sec. 5) as constraints in the optimization.  ... 
doi:10.1007/978-3-319-46484-8_22 fatcat:sdmmq5ukmffordivhxkvx3j7e4

A quasi-dense approach to surface reconstruction from uncalibrated images

M. Lhuillier, L. Quan
2005 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This fills the gap of insufficiency of the sparse approach for surface reconstruction, essential for modeling and visualization applications.  ...  More importantly, the quasi-dense approach delivers a high density of reconstructed 3D points on which a surface representation can be reconstructed.  ...  Therefore, instead of directly using global geometric constraints encoded by a fundamental matrix, we first use local smoothness constraints encoded by local planar homography : the quasi-dense pixel correspondences  ... 
doi:10.1109/tpami.2005.44 pmid:15747796 fatcat:exh235753jaxjlgzi6vlfgh2e4

Extended Hermite Radial Basis Functions for Sparse Contours Interpolation

Deyun Zhong, Liguan Wang, Lin Bi
2020 IEEE Access  
In this paper, we present an extended Hermite radial basis functions interpolant for surface reconstruction of sparse contours that allows for shape control with interactive constraints.  ...  It is useful when the method interpolates sparse data that satisfies all the constraints but exhibits an undesirable trend of shape.  ...  FIGURE 7 . 7 Comparison of reconstructions from sparse sections (a) using the method of Lu et al.  ... 
doi:10.1109/access.2020.2982802 fatcat:regq2ds6gzbmjold7sr7qw5m5i

Temporally coherent 4D reconstruction of complex dynamic scenes [article]

Armin Mustafa, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2016 arXiv   pre-print
Sparse-to-dense temporal correspondence is integrated with joint multi-view segmentation and reconstruction to obtain a complete 4D representation of static and dynamic objects.  ...  Robust joint segmentation and reconstruction of dynamic objects is achieved by introducing a geodesic star convexity constraint.  ...  Dynamic regions using the sparse feature matching to obtain an initial ob- are identified using temporal correspondence of sparse 3D ject reconstruction.  ... 
arXiv:1603.03381v2 fatcat:hvo5vh55arbz3iaqrij7fvvslu

Reconstructing Sinus Anatomy from Endoscopic Video – Towards a Radiation-free Approach for Quantitative Longitudinal Assessment [article]

Xingtong Liu, Maia Stiber, Jindan Huang, Masaru Ishii, Gregory D. Hager, Russell H. Taylor, Mathias Unberath
2020 arXiv   pre-print
We demonstrate the effectiveness and accuracy of our method on in and ex vivo data where we compare to sparse reconstructions from Structure from Motion, dense reconstruction from COLMAP, and ground truth  ...  We present a patient-specific, learning-based method for 3D reconstruction of sinus surface anatomy directly and only from endoscopic videos.  ...  The second row displays surface reconstructions estimated using the proposed method based on the sparse reconstruction.  ... 
arXiv:2003.08502v2 fatcat:n3i7xdrohbcwhcakyhabfac5ee

Reconstruction of Cell Focal Adhesions using Physical Constraints and Compressive Regularization

Joshua C. Chang, Yanli Liu, Tom Chou
2017 Biophysical Journal  
surface stress while preserving boundaries.  ...  By minimizing the objective function subject to a number of important physically motivated constraints, we are able to efficiently reconstruct stress fields with localized structure from simulated and  ...  Popescu for sharing their preliminary data on cell-induced substrate deformation measured using Hilbert phase dynamometry.  ... 
doi:10.1016/j.bpj.2017.09.021 pmid:29212006 pmcid:PMC5738527 fatcat:cq2l7yl52zacroiata2657unue

Monocular Template-Based Reconstruction of Smooth and Inextensible Surfaces [chapter]

Florent Brunet, Richard Hartley, Adrien Bartoli, Nassir Navab, Remy Malgouyres
2011 Lecture Notes in Computer Science  
We then present an approach that reconstructs a smooth 3D surface based on Free-Form Deformations. The surface is represented as a smooth map from the template image space to the 3D space.  ...  We present different approaches to reconstructing an inextensible surface from point correspondences between an input image and a template image representing a flat reference shape from a frontoparallel  ...  It is thus necessary to use additional constraints ensuring the consistency of the reconstructed surface.  ... 
doi:10.1007/978-3-642-19318-7_5 fatcat:g7of6oibwrfd7jbsk2u67adioa

Shading-based refinement on volumetric signed distance functions

Michael Zollhöfer, Angela Dai, Matthias Innmann, Chenglei Wu, Marc Stamminger, Christian Theobalt, Matthias Nießner
2015 ACM Transactions on Graphics  
In order to enable the efficient reconstruction of sub-millimeter detail, we store and process our surface using a sparse voxel hashing scheme which we augment by introducing a grid hierarchy.  ...  Exploiting the shading cues from the RGB data allows us to obtain reconstructions at previously unseen resolutions within only a few seconds.  ...  Additionally, operating on an implicit surface representation gives our approach versatility, as implicit surface representations are used in many other reconstruction approaches; e.g., using other active  ... 
doi:10.1145/2766887 fatcat:yflg5nbvazct7hz224pynzkkdi

Simple and Efficient Mesh Editing with Consistent Local Frames

Nikolas Paries, Patrick Degener, Reinhard Klein
2007 15th Pacific Conference on Computer Graphics and Applications (PG'07)  
In particular, it enforces conformal surface deformations so that local texture features are preserved.  ...  Both results in contra-intuitive surface deformation. Existing non-linear approaches do not show these problems. However, they are comparatively slow and considerably more complex.  ...  The corresponding non-linear reconstruction problem is solved using an iterative optimization.  ... 
doi:10.1109/pg.2007.43 dblp:conf/pg/PariesDK07 fatcat:2ppscub4qrhr7dims2pqsmqsye

Non-textured Objects Visual SLAM Using Pola-rization 3D Reconstruction

Han Jiale, Zhang Jingmei, Zhao Yongqiang
2021 Array  
shows that the effect of our visual SLAM method is better than that of the existing common SLAM method in reconstructing the surface shape of non-textured objects.  ...  the depth of the textured object, then multi-view normal vector constraints are fused to carry out 3D reconstruction, and finally, in the process of depth propagation, polarized light field information  ...  However, this method can obtain the texture-free surface shape by using polarization 3D reconstruction, so it can get a better reconstruction result.  ... 
doi:10.1016/j.array.2021.100066 fatcat:vokk734zgvgxfionsbirt6xm54

SURFACE CAMERA (SCAM) LIGHT FIELD RENDERING

JINGYI YU, LEONARD MCMILLAN, STEVEN GORTLER
2004 International Journal of Image and Graphics  
All rays consistent with a given correspondence are implicitly represented using a new auxiliary data structure, which we call a surface camera, or scam.  ...  In this article we present a new variant of the light field representation that supports improved image reconstruction by accommodating sparse correspondence information.  ...  Our approach first factors all of the rays associated with the constraint plane of each correspondence using a special data structure called "surface camera" or scam.  ... 
doi:10.1142/s0219467804001567 fatcat:j6zrqg6yfzdmhk54esvbd7fbjq

Joint Semantic Segmentation and 3D Reconstruction from Monocular Video [chapter]

Abhijit Kundu, Yin Li, Frank Dellaert, Fuxin Li, James M. Rehg
2014 Lecture Notes in Computer Science  
From monocular image sequence, we first obtain 2D semantic segmentation, sparse 3D reconstruction and camera poses.  ...  We make use of class specific semantic cues that constrain the 3D structure in areas, where multiview constraints are weak.  ...  Joint Semantic Segmentation and 3D Reconstruction  ... 
doi:10.1007/978-3-319-10599-4_45 fatcat:cy5tsih6cndnrcymjvk7boxoiy
« Previous Showing results 1 — 15 out of 18,614 results