cse590 v multi view reconstruction n.
Download
Skip this Video
Download Presentation
CSE590 V : Multi-View Reconstruction

Loading in 2 Seconds...

play fullscreen
1 / 30

CSE590 V : Multi-View Reconstruction - PowerPoint PPT Presentation


  • 166 Views
  • Uploaded on

CSE590 V : Multi-View Reconstruction. Avanish Kushal. Multi-View Reconstruction Preserving Weakly-Supported Surfaces [CVPR 2011]. Michael Jancosek Tomas Padjla. Motivation. Reconstruct Surfaces that do not have support in the input 3d point cloud (low textured walls, windows).

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'CSE590 V : Multi-View Reconstruction' - jael-little


Download Now An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
multi view reconstruction preserving weakly supported surfaces cvpr 2011

Multi-View Reconstruction Preserving Weakly-Supported Surfaces [CVPR 2011]

Michael Jancosek

Tomas Padjla

motivation
Motivation
  • Reconstruct Surfaces that do not have support in the input 3d point cloud (low textured walls, windows)
robust and efficient surface reconstruction from range data cgf 09

Robust and Efficient surface reconstruction from range-data[CGF- 09]

P. Labatut

J. P. Pons

R. Keriven

problem definition
Problem Definition
  • Reconstruct a surface from a set of merged scans (noisy and outliers)
related work
Related Work
  • 2 Primary Themes
    • Implicit Surfaces (Poisson Surface Reconstruction)
    • Delaunay Methods
algorithm
Algorithm
  • Perform a Delaunay Triangulation/Tetrahedralizationof the 3d point cloud+ cameras/sensors.
algorithm1
Algorithm
  • Perform a Delaunay Triangulation/Tetrahedralizationof the 3d point cloud+ cameras/sensors.
algorithm2
Algorithm
  • Construct adirected graph
    • Each tetrahedron is a vertex
algorithm3
Algorithm
  • Construct a directed graph
    • Each tetrahedron is a vertex
algorithm4
Algorithm
  • Construct a directed graph
    • Each tetrahedron is a vertex
algorithm5
Algorithm
  • Find an s-t cutset of the directed graph
    • An additional s & t vertex
algorithm6
Algorithm
  • Find an s-t cutset of the directed graph
    • The s-t cutset gives the surface
formulation
Formulation

: Visibility Information from points, cameras.

: Quality of reconstructed surface in terms of size of triangles.

multi view reconstruction preserving weakly supported surfaces cvpr 20111

Multi-View Reconstruction Preserving Weakly-Supported Surfaces[CVPR 2011]

Michael Jancosek

Tomas Padjla

problem definition1
Problem Definition
  • Reconstruct Surfaces that do not have support in the input 3d point cloud (low textured walls, windows)

Input Image Point Cloud Reconstructed Surface

using CFG 09

key claim
Key Claim
  • Large Jump in Free Space Support as we go from outside to inside.
  • Even true for weakly supported surfaces.
weakly supported surfaces3
Weakly Supported Surfaces
  • Ws > Wt -> creates wrong cut.
results1
Results

INPUT IMAGE POINT CLOUD

CFG-09 OUR METHOD

results2
Results

INPUT IMAGE POINT CLOUD

CFG-09 OUR METHOD

results3
Results

INPUT IMAGE POINT CLOUD

CGF-09 OUR METHOD

discussion
Discussion
  • How good is the claim about free space jumps ?
  • What should be the multiplication term ?
ad