New light field depth estimation benchmark

We recently published a new light field benchmark at ACCV 2016 in a collaboration with the HCI. The main  features are

  • a new synthetic dataset with 24 carefully designed scenes, which overcomes technical shortcomings of previous datasets.
  • novel error measures and evaluation modalities enabling comprehensive and detailed characterizations of algorithm results.
  • an initial performance analysis of four state-of-the-art light field algorithms and one multi-view stereo algorithm.
  • a benchmarking website and an evaluation toolkit to provide researchers with the necessary tools to facilitate algorithm evaluation.

The benchmarking website is hosted at lightfield-analysis.net. Please refer to our ACCV paper in case you use any of the datasets.

 

Code - structure from motion and bundle adjustment for light field cameras

Accompanying or ICCV 2015 and ACCV 2016 papers, we have code and referece datasets available to perform structure from motion and bundle adjustment for light field cameras. Please download from here:

Code (Matlab)

Lytro dataset (3 views)

Synthetic dataset (20 views)

If you make use of the code in your own work, please cite the following papers:

@string{iccv="IEEE International Conference on Computer Vision (ICCV)"}@InProceedings{JSG15:iccv, author = {O. Johannsen and A. Sulc and B. Goldluecke}, title = {On Linear Structure from Motion for Light Field Cameras}, booktitle = iccv, year = {2015}, } 

@string{accv="Asian Conference on Computer Vision (ACCV)"}@InProceedings{JSMG16:accv, author = {O. Johannsen and A. Sulc and N. Marniok and B. Goldluecke}, title = {Layered scene reconstruction from multiple light field camera views}, booktitle = accv, year = {2016}, }

 

Code - intrinsic light fields

Accompanying or ACCV 2016 paper, we have code available to perform intrinsic light field decomposition. Example datasets are included. Please download here.

If you make use of the code or datasets in your own work, please cite the following paper:

@string{accv="Asian Conference on Computer Vision (ACCV)"} @InProceedings{AG16:accv,  author = {A. Alperovich and B. Goldluecke},  title = {A variational model for intrinsic light field decomposition},  booktitle = accv,  year = {2016}, }

 

HCI light field database

The HCI light field database recently went offline after their web page was restructured. As we co-authored the paper and there is still lots of demand for them, we temporarily host the data sets on our own servers.

The following script points to modified download locations:

Modified download script for HCI light field database

Please refer to our VMV paper details, and cite it in case you use any of the datasets.

 

Code - convex optimization

We develop the open source library cocolib, a C++/CUDA toolkit for variational image analysis and continuous global optimization. The focus lies on the minimization of functionals of the type

\( E(u) = J(u) + F(u) \)

where \( u \) is an image (i.e. vector-valued function on a grid), \( J \) is a convex regularizer, and \( F \) a (usually) convex data term. The library comes with a command line tool and Matlab interface, as well as example code for most of the available algorithms.

A number of generic and more specialized solvers are implemented, focusing on linear inverse problems and multi-label segmentation with various models for regularization and data terms. 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.

Please see the project home page for more information.

Note that the project is orphaned since 2015 - as Matlab has a very decent GPU support, we now usually use a combination of Matlab and CUDA C++ plugins for development.