cocolib / light field suite

beta

CUDA library for continuous optimization and light field analysis

5.0 Stars (1)
25 Downloads (This Week)
Last Update:
Download Release 6
Browse All Files
Mac Linux

Description

Library for continuous convex optimization in image analysis, together with a command line tool and Matlab interface.

Implements several recent algorithms for inverse problems and image segmentation with total variation regularizers and vectorial multilabel transition costs.

Also included is a suite for variational light field analysis, which ties into the HCI light field benchmark set and givens reference implementations for a number of our recently published algorithms.

*** NOTE: documentation on the SourceForge page is outdated and not updated anymore, please visit http://cocolib.net ***

cocolib / light field suite Web Site

Features

  • CUDA Implementations of recent algorithms for variational image analysis
  • (Growing) subset implemented in OpenCL
  • Same subset with Matlab interface
  • Library and example: command line tool for image processing
  • Vectorial total variation: inverse problems, inpainting, optical flow
  • Total variation: inverse problems, inpainting and segmentation
  • Total Curvature: inverse problems, inpainting and segmentation
  • Vectorial Multilabel problems: linear, cyclic and Potts interactions
  • Light field analysis: depth estimation, regularization, segmentation

Update Notifications





User Ratings

★★★★★
★★★★
★★★
★★
1
0
0
0
0
ease 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
features 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
design 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
support 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
Write a Review

User Reviews

  • shwbaek
    1 of 5 2 of 5 3 of 5 4 of 5 5 of 5

    Thank you for the nice work

    Posted 10/13/2013
Read more reviews

Additional Project Details

Languages

English

Intended Audience

Science/Research

User Interface

Command-line

Programming Language

C++

Registered

2011-09-08

Icons must be PNG, GIF, or JPEG and less than 1 MiB in size. They will be displayed as 48x48 images.