Research
Main.Research History
Hide minor edits - Show changes to output
Added lines 10-13:
\\
\\
\\
%width=200px% Attach:FigureMiningLogo.png%center%
\\
\\
%width=200px% Attach:FigureMiningLogo.png%center%
Added lines 33-36:
\\
[ [[Biomedical Figure and Text Mining | Project Webpage]] ]
Changed line 32 from:
!!! %center%Hybrid Approach for Extracting Knowledge from Biomedical Literature
to:
!!! %center%Biomedical Figure and Text Mining
Changed lines 36-38 from:
[ [[http://annotation.dbi.udel.edu/image_mining/index.php | Automatic Extraction of Figure-Caption Pairs from PDF Files]] ]
to:
[ [[Automatic Extraction of Figure-Caption Pairs from PDF Files | Automatic Extraction of Figure-Caption Pairs from PDF Files]] ]
In this paper we present a novel approach for automatically extracting figure-caption pairs from Biomedical publications in PDF format.
In this paper we present a novel approach for automatically extracting figure-caption pairs from Biomedical publications in PDF format.
Changed line 36 from:
[ [[http://annotation.dbi.udel.edu/image_mining/index.php | Automatic Extraction of Figure-Caption Pairs]] ]
to:
[ [[http://annotation.dbi.udel.edu/image_mining/index.php | Automatic Extraction of Figure-Caption Pairs from PDF Files]] ]
Changed line 36 from:
[ [[Automatic Extraction of Figure-Caption Pairs | http://annotation.dbi.udel.edu/image_mining/index.php]] ]
to:
[ [[http://annotation.dbi.udel.edu/image_mining/index.php | Automatic Extraction of Figure-Caption Pairs]] ]
Changed line 36 from:
[ [[Automatic Extraction of Figure-Caption Pairs | Automatic Extraction of Figure-Caption Pairs]] ]
to:
[ [[Automatic Extraction of Figure-Caption Pairs | http://annotation.dbi.udel.edu/image_mining/index.php]] ]
Added lines 28-37:
\\
\\
\\
\\
!!! %center%Hybrid Approach for Extracting Knowledge from Biomedical Literature
[ [[Automatic Extraction of Figure-Caption Pairs | Automatic Extraction of Figure-Caption Pairs]] ]
In
\\
\\
\\
!!! %center%Hybrid Approach for Extracting Knowledge from Biomedical Literature
[ [[Automatic Extraction of Figure-Caption Pairs | Automatic Extraction of Figure-Caption Pairs]] ]
In
Changed lines 13-14 from:
[ [[tree modeling | project webpage]] ]
to:
[ [[tree modeling | tree modeling]] ]
Added lines 27-28:
[[Image Modeling | Image Modeling Project Webpage]]
Changed lines 21-25 from:
\\In this paper we present an image-based system for recovering complex 3D model of real roots. Our method is able to recover accurate 3D root geometry. Compared to existing reconstruction approaches, our system can accurately recover complex topology and geometry of 3D roots using only a few set of images.
to:
\\
\\
[ [[root modeling | root modeling]] ]
In this paper we present an image-based system for recovering complex 3D model of real roots. Our method is able to recover accurate 3D root geometry. Compared to existing reconstruction approaches, our system can accurately recover complex topology and geometry of 3D roots using only a few set of images.
\\
[ [[root modeling | root modeling]] ]
In this paper we present an image-based system for recovering complex 3D model of real roots. Our method is able to recover accurate 3D root geometry. Compared to existing reconstruction approaches, our system can accurately recover complex topology and geometry of 3D roots using only a few set of images.
Changed lines 19-22 from:
to:
\\
\\
\\In this paper we present an image-based system for recovering complex 3D model of real roots. Our method is able to recover accurate 3D root geometry. Compared to existing reconstruction approaches, our system can accurately recover complex topology and geometry of 3D roots using only a few set of images.
Our system can generate fine geometry of roots in few minutes with minimal user intervention, making it more suitable for large scale applications.
\\
\\In this paper we present an image-based system for recovering complex 3D model of real roots. Our method is able to recover accurate 3D root geometry. Compared to existing reconstruction approaches, our system can accurately recover complex topology and geometry of 3D roots using only a few set of images.
Our system can generate fine geometry of roots in few minutes with minimal user intervention, making it more suitable for large scale applications.
Changed line 9 from:
%width=200px,height=200px% Attach:root1.jpg%center%
to:
%width=200px height=200px% Attach:root1.jpg%center%
Changed line 9 from:
%width=200px% Attach:root1.jpg%center%
to:
%width=200px,height=200px% Attach:root1.jpg%center%
Changed line 9 from:
%width=200px% Attach:smallm1v2.jpg%center%
to:
%width=200px% Attach:root1.jpg%center%
Changed line 18 from:
[ [[Image Modeling | Image Modeling Project Webpage]] ]
to:
[[Image Modeling | Image Modeling Project Webpage]]
Added lines 6-8:
\\
\\
%width=200px% Attach:smallm1v2.jpg%center%
\\
%width=200px% Attach:smallm1v2.jpg%center%
Deleted lines 19-22:
\\
\\
%width=200px% Attach:root1.jpg%center%
Added lines 17-20:
(:cell:)
\\
\\
%width=200px% Attach:root1.jpg%center%
\\
\\
%width=200px% Attach:root1.jpg%center%
Changed lines 9-10 from:
[ [[Image Modeling | project webpage]] ]
to:
[ [[tree modeling | project webpage]] ]
Added lines 14-15:
[ [[Image Modeling | Image Modeling Project Webpage]] ]
Added lines 12-14:
Our solution actively integrates 2D and 3D tree topology as shape priors in the reconstruction process and it is able to accurately recover complex tree geometry with minimal user interventions.
Changed line 11 from:
to:
In this project we developed a novel approach for reconstructing 3D models of tree-like objects by using a sparse set of viewpoints. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. In contrast, our approach focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
Changed line 11 from:
Image-based modeling applies a sparse set of images from different viewpoints to construct a 3D model of tree-like objects. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. In contrast, our approach focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
to:
Image-based modeling applies a sparse set of images from different viewpoints to construct a 3D model of tree-like objects. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. In contrast, our approach focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
Changed line 10 from:
!!!Image based 3D modeling
to:
!!! %center%Image based 3D modeling
Changed line 13 from:
Image-based modeling applies a sparse set of images from different viewpoints to construct a 3D model of tree-like objects. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. Our method focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
to:
Image-based modeling applies a sparse set of images from different viewpoints to construct a 3D model of tree-like objects. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. In contrast, our approach focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
Changed lines 11-14 from:
[ [[tree modeling | project]] ] ''Computer Graphics Forum 29(7): 2075-2082 (2010)''\\
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu
[-We present a novel image-based technique for modeling complex unfoliaged trees. Existing tree modeling tools either require capturing a large number of views for dense 3D reconstruction or rely on user inputs and botanic rules to synthesize natural-looking tree geometry. In this paper, we focus on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images. Our solution directly integrates 2D=3D tree topology as shape priors into the modeling process. For each input view, we first estimate a 2D skeleton graph from its matte image and then find a 2D skeleton tree from the graph by imposing tree topology. We develop a simple but effective technique for computing the optimal 3D skeleton tree most consistent with the 2D skeletons. For each edge in the 3D skeleton tree, we further apply volumetric reconstruction to recover its corresponding curved branch. Finally, we use piecewise cylinders to approximate each branch from the volumetric results. We demonstrate our framework on a variety of trees to illustrate the robustness and usefulness of our technique.-]
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu
[-We present
to:
[ [[tree modeling | project]] ]
Image-based modeling applies a sparse set of images from different viewpoints to construct a 3D model of tree-like objects. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. Our method focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
Image-based modeling applies a sparse set of images from different viewpoints to construct a 3D model of tree-like objects. Previous approaches either requires a dense set of images or relies on computational tomography for dense point cloud registration. Our method focuses on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images.
Changed line 10 from:
!!!Image-based Modeling
to:
!!!Image based 3D modeling
Changed line 10 from:
!!!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
to:
!!!Image-based Modeling
Changed line 11 from:
[ [[tree modeling | project]] ] ''Computer Graphics Forum 29(7): 2075-2082 (2010)''
to:
[ [[tree modeling | project]] ] ''Computer Graphics Forum 29(7): 2075-2082 (2010)''\\
Changed lines 2-6 from:
(:cell:) \\ \\ \\%width=200px% Attach:smallm1v2.jpg%center%
to:
(:cell:)
\\
\\
\\
%width=200px% Attach:smallm1v2.jpg%center%
\\
\\
\\
%width=200px% Attach:smallm1v2.jpg%center%
Changed line 2 from:
(:cell:) %width=200px% Attach:smallm1v2.jpg%center%
to:
(:cell:) \\ \\ \\%width=200px% Attach:smallm1v2.jpg%center%
Changed lines 6-7 from:
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu\\
to:
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu
Changed lines 6-7 from:
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu
to:
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu\\
Changed lines 7-8 from:
We present a novel image-based technique for modeling complex unfoliaged trees. Existing tree modeling tools either require capturing a large number of views for dense 3D reconstruction or rely on user inputs and botanic rules to synthesize natural-looking tree geometry. In this paper, we focus on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images. Our solution directly integrates 2D=3D tree topology as shape priors into the modeling process. For each input view, we first estimate a 2D skeleton graph from its matte image and then find a 2D skeleton tree from the graph by imposing tree topology. We develop a simple but effective technique for computing the optimal 3D skeleton tree most consistent with the 2D skeletons. For each edge in the 3D skeleton tree, we further apply volumetric reconstruction to recover its corresponding curved branch. Finally, we use piecewise cylinders to approximate each branch from the volumetric results. We demonstrate our framework on a variety of trees to illustrate the robustness and usefulness of our
to:
[-We present a novel image-based technique for modeling complex unfoliaged trees. Existing tree modeling tools either require capturing a large number of views for dense 3D reconstruction or rely on user inputs and botanic rules to synthesize natural-looking tree geometry. In this paper, we focus on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images. Our solution directly integrates 2D=3D tree topology as shape priors into the modeling process. For each input view, we first estimate a 2D skeleton graph from its matte image and then find a 2D skeleton tree from the graph by imposing tree topology. We develop a simple but effective technique for computing the optimal 3D skeleton tree most consistent with the 2D skeletons. For each edge in the 3D skeleton tree, we further apply volumetric reconstruction to recover its corresponding curved branch. Finally, we use piecewise cylinders to approximate each branch from the volumetric results. We demonstrate our framework on a variety of trees to illustrate the robustness and usefulness of our technique.-]
Changed lines 5-7 from:
[ [[tree modeling | project]] ]
''Computer Graphics Forum 29(7): 2075-2082 (2010)''
''Computer Graphics Forum 29(7): 2075-2082 (2010)''
to:
[ [[tree modeling | project]] ] ''Computer Graphics Forum 29(7): 2075-2082 (2010)''
Changed line 7 from:
to:
[-small-]
Added line 6:
Added line 10:
We present a novel image-based technique for modeling complex unfoliaged trees. Existing tree modeling tools either require capturing a large number of views for dense 3D reconstruction or rely on user inputs and botanic rules to synthesize natural-looking tree geometry. In this paper, we focus on faithfully recovering real instead of realistically-looking tree geometry from a sparse set of images. Our solution directly integrates 2D=3D tree topology as shape priors into the modeling process. For each input view, we first estimate a 2D skeleton graph from its matte image and then find a 2D skeleton tree from the graph by imposing tree topology. We develop a simple but effective technique for computing the optimal 3D skeleton tree most consistent with the 2D skeletons. For each edge in the 3D skeleton tree, we further apply volumetric reconstruction to recover its corresponding curved branch. Finally, we use piecewise cylinders to approximate each branch from the volumetric results. We demonstrate our framework on a variety of trees to illustrate the robustness and usefulness of our technique.
Added lines 6-7:
''Computer Graphics Forum 29(7): 2075-2082 (2010)''
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu
Luis D. Lopez, Yuanyuan Ding, Jingyi Yu
Changed line 5 from:
[[tree modeling | project]]
to:
[ [[tree modeling | project]] ]
Changed lines 5-6 from:
[[ treeModeling]]
to:
[[tree modeling | project]]
Changed line 4 from:
!!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
to:
!!!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
Changed lines 3-4 from:
(:cell:) !! Modeling Complex Unfoliaged Trees from a Sparse Set of Images
to:
(:cell:)
!!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
!!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
Changed lines 3-4 from:
(:cell:) !!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
to:
(:cell:) !! Modeling Complex Unfoliaged Trees from a Sparse Set of Images
Changed line 3 from:
(:cell:) c1
to:
(:cell:) !!Modeling Complex Unfoliaged Trees from a Sparse Set of Images
Changed line 2 from:
(:cell:) %width=250px% Attach:smallm1v2.jpg%center%
to:
(:cell:) %width=200px% Attach:smallm1v2.jpg%center%
Changed line 2 from:
(:cell:) Attach:smallm1v2.jpg%center%
to:
(:cell:) %width=250px% Attach:smallm1v2.jpg%center%
Changed line 2 from:
(:cell:) b1
to:
(:cell:) Attach:smallm1v2.jpg%center%
Changed line 1 from:
(:table border=0 cellpadding=5 cellspacing=0:)
to:
(:table border=0 cellpadding=5 cellspacing=5:)
Added lines 1-2:
(:table border=0 cellpadding=5 cellspacing=0:)
(:tableend:)
(:tableend:)