Personal information

Computer Vision, Machine Learning, Physics-based Vision, Scene Understanding, Intrinsic Image Decomposition, Color Constancy, Illumination, Shading, Reflectance, Albedo

Biography

I obtained my PhD degree in 2021 at University of Amsterdam under the supervision of Prof. Theo Gevers. My doctoral study was fully funded by the EUHorizon2020 program within the Trimbot2020 project - the first ever autonomous gardening robot. My main research topic was intrinsic image decomposition, and my doctoral thesis is titled Physics-aware Learning of Intrinsic Images.

During my PhD, I also conducted research on semantic segmentation, object detection and recognition, instance segmentation, surface normal estimation, illumination estimation, optical flow, edge detection, and also traditional image processing, model-based machine learning, deep learning, and generative adversarial networks.

I received my Master's Degree in Data Engineering with distinction from Tampere University of Technology, Finland in 2016. I performed my thesis "Camera Sensor Invariant Auto White Balance Algorithm Weighting" under the supervison of Prof. Moncef Gabbouj and Dr. Jarno Nikkanen, in collaboration with Intel. During my studies, I also carried out an internship at Microsoft Finland, where I worked on image sharpness optimization and auto white balance problems.

My research interests include computer vision and pattern recognition, especially physics-based representations, invariant descriptors, general scene understanding, color image processing, and deep learning.

Activities

Employment (3)

University of Amsterdam: Amsterdam, NL

2016-05 to 2020-09 | Computer Vision and Deep Learning Researcher (Computer Vision Lab)
Employment
Source: Self-asserted source
Anil Baslamisli

Intel Corporation: Tampere, FI

2015-09 to 2016-05 | Computer Vision Research Intern (Imaging Algorithms)
Employment
Source: Self-asserted source
Anil Baslamisli

Microsoft (Finland): Tampere, FI

2015-05 to 2015-08 | Computer Vision Research Intern (Imaging Algorithms)
Employment
Source: Self-asserted source
Anil Baslamisli

Education and qualifications (3)

University of Amsterdam: Amsterdam, Noord-Holland, NL

2016-05 to 2020-09 | PhD in Computer Vision and Machine Learning (Informatics Institute)
Education
Source: Self-asserted source
Anil Baslamisli

Tampere University: Tampere, FI

2014-08 to 2016-05 | MSc in Data Engineering (Information Technology)
Education
Source: Self-asserted source
Anil Baslamisli

Middle East Technical University : Morphou, CY

2010-09 to 2014-06 | BSc in Computer Engineering (Engineering)
Education
Source: Self-asserted source
Anil Baslamisli

Works (10)

SAR image edge detection: review and benchmark experiments

International Journal of Remote Sensing
2022-07-18 | Journal article
Contributors: M. J. Meester; A. S. Baslamisli
Source: check_circle
Crossref

ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

International Journal of Computer Vision
2021-08 | Journal article
Part of ISSN: 0920-5691
Part of ISSN: 1573-1405
Source: Self-asserted source
Anil Baslamisli
grade
Preferred source (of 2)‎

Invariant Descriptors for Intrinsic Reflectance Optimization

Journal of the Optical Society of America A
2021-06-01 | Journal article
Part of ISSN: 1084-7529
Part of ISSN: 1520-8532
Source: Self-asserted source
Anil Baslamisli

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

Computer Vision and Image Understanding
2021-04 | Journal article
Part of ISSN: 1077-3142
Source: Self-asserted source
Anil Baslamisli

Joint Learning of Intrinsic Images and Semantic Segmentation

2018 European Conference on Computer Vision (ECCV)
2018 | Conference paper
Part of ISBN: 9783030012304
Part of ISBN: 9783030012311
Part of ISSN: 0302-9743
Part of ISSN: 1611-3349
Source: Self-asserted source
Anil Baslamisli

Color Constancy by GANs: An Experimental Survey

2018-12-07 | Preprint
Source: Self-asserted source
Anil Baslamisli

Automatic Generation of Dense Non-rigid Optical Flow

2018-12-05 | Preprint
Source: Self-asserted source
Anil Baslamisli

Three for One and One for Three: Flow, Segmentation, and Surface Normals

2018 British Machine Vision Conference (BMVC)
2018-09 | Conference paper
Source: Self-asserted source
Anil Baslamisli

CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image Decomposition

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2018-06 | Conference paper
Source: Self-asserted source
Anil Baslamisli

Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance Segmentation

2021 IEEE/CVF International Conference on Computer Vision
Conference paper
Source: Self-asserted source
Anil Baslamisli