Dr. Shida Beigpour

mail:

address:

Universität Siegen (University of Siegen)
Lehrstuhl für Computergrafik
57068 Siegen

As of July 2016, I am a Lise Meitner Award Fellow at the Max Planck Institute for Informatik. My new page at MPI can be accessed here.

Previously I was a Senior Research Scientist at the Chair for Computer Graphics and Multimedia Systems of the University of Siegen, Germany. And before that I held a position as an associated professor at the Faculty of Computer Science and Media Technology in Gjovik University College (Høgskolen i Gjøvik) and the Norwegian Colour and Visual Computing Laboratory.
In 2013, I've received my PhD title at the Computer Vision Center (CVC) of the Universitat Autonoma de Barcelona (UAB), Barcelona, Spain. Before that, I've obtained my master degree in Artificial Intelligence and Computer Vision in 2008 from UAB.

Complete CV

Downloads:

DATASETS:

Multi-view Multi-illuminant Intrinsic Dataset (MVMII):

a novel high-resolution multi-view dataset of complex multi-illuminant scenes with precise reflectance and shading ground-truth as well as raw depth and 3D point cloud. Our dataset challenges the intrinsic image methods by providing complex coloured cast shadows, highly textured and colourful surfaces, and specularity.

Low Resolution Version : Download link - coming soon
High Resolution Version : Download link - coming soon

For non-commercial use only. If you use this dataset, please cite: S. Beigpour, M. Lan Ha, S. Kunz, A. Kolb, V. Blanz - Multi-view Multi-illuminant Intrinsic Dataset In Proc. British Machine Vision Conference (BMVC), 2016

Multi-Illuminant Intrinsic Image Dataset (MIII):

A real-capture intrinsic image dataset with accurate pixel-wise ground-truth for intrinsic image estimation benchmarking in complex multi-illuminant scenes. Please note that the "High Resolution Version" of the data also contains the corresponding coarse depth images.

Low Resolution Version : Download link - 10 MB - Without the depth images.
High Resolution Version : Download link - 550 MB - This folder includes the corresponding depth images.

For non-commercial use only. If you use this dataset, please cite: S. Beigpour, A. Kolb, and S. Kunz, A Comprehensive Multi-Illuminant Dataset for Benchmarking of Intrinsic Image Algorithms, Proceedings of IEEE International Conference on Computer Vision (ICCV), December 2015

Multi-Illuminant Multi-Object (MIMO) :

Dataset for multi-illuminant color constancy benchmarking with accurate pixel-wise Groundtruth.
Download link
For non-commercial use only. If you use this dataset, please cite: Shida Beigpour, Christian Riess, Joost van de Weijer, Elli Angelopoulou - Multi-Illuminant Estimation with Conditional Random Fields In IEEE Transactions on Image Processing (TIP), 23(1), 2014, pages 83-95

Synthetic intrinsic image dataset:
Computer graphics generated dataset for intrinsic estimation benchmarking in complex scenes.
Download link
Matlab code to evaluate intrinsic image algorithms can be downloaded here. For more info please visit Project Page.
For non-commercial use only. If you use this dataset, please cite: Shida Beigpour, Marc Serra, Joost van de Weijer, Robert Benavente, Maria Vanrell, Olivier Penacchio, Dimitris Samaras - Intrinsic Image Evaluation On Synthetic Complex Scenes In IEEE International Conference on Image Processing (ICIP), 2013

Colourlab Image Database: Multi-Illuminant scene (CID:MI):
Download link
For non-commercial use only. If you use this dataset, please cite: Imtiaz Masud Ziko, Shida Beigpour, Jon Yngve Hardeberg - Design and Creation of a Multi-Illuminant Scene Image Dataset In Image and Signal Processing, Lecture Notes in Computer Science, 8509, 2014, pages 531-538

Open-source codes:

Object Recoloring based on Intrinsic Image Estimation:
Demo code for recoloring in matlab.
Download link
For non-commercial use only. If you use this code, please cite: Shida Beigpour, Joost van de Weijer - Object Recoloring based on Intrinsic Image Estimation In IEEE International Conference on Computer Vision (ICCV), 2011

Posters, presentations, suplementary materials:

2015: A Comprehensive Multi-Illuminant Dataset for Benchmarking of Intrinsic Image Algorithms:

Supplementary Video
Poster

For non-commercial use only. If you use any material from these sources please cite: Shida Beigpour, Andreas Kolb, Sven Kunz - A Comprehensive Multi-Illuminant Dataset for Benchmarking of Intrinsic Image Algorithms In Proc. IEEE International Conference on Computer Vision (ICCV), 2015

2014: Light, Color, and Surface Reflectance:
Short presentation
Download link
For non-commercial use only. If you use any material from these slides please cite: the relevant publication indicated in the slides. Pages 9,11, 63-64 contain materials from other sources not belonging to the current author.

2013: Intrinsic Image Evaluation On Synthetic Complex Scenes:

Poster (As presented at the conference)
For non-commercial use only. If you use any material from these sources please cite: Shida Beigpour, Marc Serra, Joost van de Weijer, Robert Benavente, Maria Vanrell, Olivier Penacchio, Dimitris Samaras - Intrinsic Image Evaluation On Synthetic Complex Scenes In IEEE International Conference on Image Processing (ICIP), 2013

2011: Object Recoloring based on Intrinsic Image Estimation:

Supplementary Video
Poster (As presented at the conference)

For non-commercial use only. If you use any material from these sources please cite: Shida Beigpour, Joost van de Weijer - Object Recoloring based on Intrinsic Image Estimation In IEEE International Conference on Computer Vision (ICCV), 2011

News

Youtube Channel CG

You are here

Dr. Shida Beigpour