Results 1 - 10
of
17
Noisy Depth Maps Fusion for Multi-view Stereo via Matrix Completion
, 2011
"... This paper introduces a general framework to fuse noisy point clouds from multi-view images of the same object. We solve this classical vision problem using a newly emerging signal processing technique known as matrix completion. With this framework, we construct the initial incomplete matrix from ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
This paper introduces a general framework to fuse noisy point clouds from multi-view images of the same object. We solve this classical vision problem using a newly emerging signal processing technique known as matrix completion. With this framework, we construct the initial incomplete matrix from the observed point clouds by all the cameras, with the invisible points by any camera denoted as unknown entries. The observed points corresponding to the same object point are put into the same row. When properly completed, the recovered matrix should have rank one, since all the columns describe the same object. Therefore, an intuitive approach to complete the matrix is by minimizing its rank subject to consistency with observed entries. In order to improve the fusion accuracy, we propose a general noisy matrix completion method called Log-sum Penalty Completion (LPC), which is particularly effective in removing outliers. Based on the Majorization-Minimization algorithm (MM), the nonconvex LPC problem is effectively solved by a sequence of convex optimizations. Experimental results on both point cloud fusion and MVS reconstructions verify the effectiveness of the proposed framework and the LPC algorithm.
Least commitment, viewpointbased, multi-view stereo
- In 3DIMPVT
, 2012
"... We address the problem of large-scale 3D reconstruction from calibrated images relying on a viewpoint-based approach. The representation is in the form of a collection of depth maps, which are fused to blend consistent depth estimates and minimize violations of visibility constraints. We adopt a lea ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
(Show Context)
We address the problem of large-scale 3D reconstruction from calibrated images relying on a viewpoint-based approach. The representation is in the form of a collection of depth maps, which are fused to blend consistent depth estimates and minimize violations of visibility constraints. We adopt a least commitment strategy by allowing multiple candidate depth values per pixel in the fusion process and deferring hard decisions as much as possible. To address the inevitable noise in the depth maps, we explicitly model its sources, namely mismatches and inaccurate 3D coordinate estimation via triangulation, by measuring two types of uncertainty and using the uncertainty estimates to guide the fusion process. To the best of our knowledge, this is the first attempt to model both geometric and correspondence uncertainty in the context of dense 3D reconstruction. We show quantitative results on datasets with ground truth that are competitive with the state of the art. Undeniably, there has been significant progress in multiview 3D reconstruction in terms of accuracy, scalability and more rigorous benchmarking [27, 28]. One question that has not been resolved yet, however, since the answer depends on the specific variant of the problem one is faced with, is which is the “best ” approach for multiview reconstruction. There are methods that achieve outstanding results on single objects surrounded by cameras
MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction∗
"... Many traditional challenges in reconstructing 3D mo-tion, such as matching across wide baselines and handling occlusion, reduce in significance as the number of unique viewpoints increases. However, to obtain this benefit, a new challenge arises: estimating precisely which cameras ob-serve which poi ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
Many traditional challenges in reconstructing 3D mo-tion, such as matching across wide baselines and handling occlusion, reduce in significance as the number of unique viewpoints increases. However, to obtain this benefit, a new challenge arises: estimating precisely which cameras ob-serve which points at each instant in time. We present a maximum a posteriori (MAP) estimate of the time-varying visibility of the target points to reconstruct the 3D motion of an event from a large number of cameras. Our algo-rithm takes, as input, camera poses and image sequences, and outputs the time-varying set of the cameras in which a target patch is visible and its reconstructed trajectory. We model visibility estimation as a MAP estimate by incorpo-rating various cues including photometric consistency, mo-tion consistency, and geometric consistency, in conjunction with a prior that rewards consistent visibilities in proximal cameras. An optimal estimate of visibility is obtained by finding the minimum cut of a capacitated graph over cam-eras. We demonstrate that our method estimates visibility with greater accuracy, and increases tracking performance producing longer trajectories, at more locations, and at higher accuracies than methods that ignore visibility or use photometric consistency alone. 1.
PatchMatch Based Joint View Selection and Depthmap Estimation
"... We propose a multi-view depthmap estimation approach aimed at adaptively ascertaining the pixel level data asso-ciations between a reference image and all the elements of a source image set. Namely, we address the question, what aggregation subset of the source image set should we use to estimate th ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
We propose a multi-view depthmap estimation approach aimed at adaptively ascertaining the pixel level data asso-ciations between a reference image and all the elements of a source image set. Namely, we address the question, what aggregation subset of the source image set should we use to estimate the depth of a particular pixel in the reference im-age? We pose the problem within a probabilistic framework that jointly models pixel-level view selection and depthmap estimation given the local pairwise image photoconsistency. The corresponding graphical model is solved by EM-based view selection probability inference and PatchMatch-like depth sampling and propagation. Experimental results on standard multi-view benchmarks convey the state-of-the art estimation accuracy afforded by mitigating spurious pixel-level data associations. Additionally, experiments on large Internet crowd sourced data demonstrate the robustness of our approach against unstructured and heterogeneous im-age capture characteristics. Moreover, the linear computa-tional and storage requirements of our formulation, as well as its inherent parallelism, enables an efficient and scalable GPU-based implementation. 1.
Robust temporally coherent Laplacian protrusion
, 2012
"... (will be inserted by the editor) ..."
(Show Context)
Author manuscript, published in "CVPR- Computer Vision and Patern Recognition- 2012 (2012)" Progressive Shape Models
"... ..."
(Show Context)
3D Shape . . . Graph Embedding and Probabilistic Matching
, 2011
"... In this book chapter we address the problem of 3D shape registration and we propose a novel technique based on spectral graph theory and probabilistic matching. Recent advancement in shape acquisition technology has led to the capture of large amounts of 3D data. Existing real-time multi-camera 3D a ..."
Abstract
- Add to MetaCart
In this book chapter we address the problem of 3D shape registration and we propose a novel technique based on spectral graph theory and probabilistic matching. Recent advancement in shape acquisition technology has led to the capture of large amounts of 3D data. Existing real-time multi-camera 3D acquisition methods provide a frame-wise reliable visual-hull or mesh representations for real 3D animation sequences The task of 3D shape analysis involves tracking, recognition, registration, etc. Analyzing 3D data in a single framework is still a challenging task considering the large variability of the data gathered with different acquisition devices. 3D shape registration is one such challenging shape analysis task. The main contribution of this chapter is to extend the spectral graph matching methods to very large graphs by combining spectral graph matching with Laplacian embedding. Since the embedded representation of a graph is obtained by inria-00590273, version 2- 10 Aug 2011 dimensionality reduction we claim that the existing spectral-based methods are not easily applicable. We discuss solutions for the exact and inexact graph isomorphism problems and recall the main spectral properties of the combinatorial graph Laplacian; We provide a novel analysis of the commute-time embedding that allows us to interpret the latter in terms of the PCA of a graph, and to select the appropriate dimension of
INRIA Grenoble Rhône-Alpes
"... In this book chapter we address the problem of 3D shape registration and we propose a novel technique based on spectral graph theory and probabilistic matching. Recent advancement in shape acquisition technology has led to the capture of large amounts of 3D data. Existing real-time multi-camera 3D a ..."
Abstract
- Add to MetaCart
(Show Context)
In this book chapter we address the problem of 3D shape registration and we propose a novel technique based on spectral graph theory and probabilistic matching. Recent advancement in shape acquisition technology has led to the capture of large amounts of 3D data. Existing real-time multi-camera 3D acquisition methods provide a frame-wise reliable visual-hull or mesh representations for real 3D animation sequences The task of 3D shape analysis involves tracking, recognition, registration, etc. Analyzing 3D data in a single framework is still a challenging task considering the large variability of the data gathered with different acquisition devices. 3D shape registration is one such challenging shape analysis task. The main contribution of this chapter is to extend the spectral graph matching methods to very large graphs by combining spectral graph matching with Laplacian embedding. Since the embedded representation of a graph is obtained by dimensionality reduction we claim that the existing spectral-based methods are not easily applicable. We discuss solutions for the exact and inexact graph isomorphism problems and recall the main spectral properties of the combinatorial graph Laplacian; We provide a novel analysis of the commute-time embedding that allows us to interpret the latter in terms of the PCA of a graph, and to select the appropriate dimension of the associated embedded metric space; We derive a unit hyper-sphere normalization for the commute-time
Enforcing Consistency of 3D Scenes with Multiple Objects Using Shape-from-Contours
"... Abstract. In this paper we present a new approach for modelling scenes with multiple 3D objects from images taken from various viewpoints. Such images are segmented using either supervised or unsupervised al-gorithms. We consider the mean-shift and support vector machines for image segmentation usin ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. In this paper we present a new approach for modelling scenes with multiple 3D objects from images taken from various viewpoints. Such images are segmented using either supervised or unsupervised al-gorithms. We consider the mean-shift and support vector machines for image segmentation using the colour and texture as features. Back-projections of segmented contours are used to enforce the consistency of the segmented contours with initial estimates of the 3D scene. A study for detecting merged objects in 3D scenes is provided as well.
