Photo of Saghi Hajisharif

Saghi Hajisharif

Principal Research Engineer

My research interests are in visual machine learning, HDR imaging, photo-realistic rendering, compressive imaging, and light fields.

Representation learning for Computational Imaging

I am a researcher in Computer Graphics and Image Processing group. I am interested in using machine learning, specifically sparse representation learning, to transform the data into lower-dimensional space to solve research problems related to computational imaging. I received a PhD in Visualization and Media technology titled "Computational Photography: High Dynamic Range and Light fields" in 2020 from Linköping University. I have an MSc in Advanced Computer Graphics from Linköping University in 2013, focusing on Image-based lighting. In 2009 I received my BSc in Computer Science from Amirkabir University in Tehran.

Publications

2024

Ehsan Miandji, Tanaboon Tongbuasirilai, Saghi Hajisharif, Behnaz Kavoosighafi, Jonas Unger (2024) FROST-BRDF: A Fast and Robust Optimal Sampling Technique for BRDF Acquisition IEEE Transactions on Visualization and Computer Graphics, Vol. 30, p. 4390-4402 (Article in journal) Continue to DOI
Ericka Johnson, Saghi Hajisharif (2024) The intersectional hallucinations of synthetic data AI & Society: The Journal of Human-Centred Systems and Machine Intelligence (Article in journal) Continue to DOI

2023

Behnaz Kavoosighafi, Jeppe Revall Frisvad, Saghi Hajisharif, Jonas Unger, Ehsan Miandji (2023) SparseBTF: Sparse Representation Learning for Bidirectional Texture Functions

2022

Param Hanji, Rafal K. Mantiuk, Gabriel Eilertsen, Saghi Hajisharif, Jonas Unger (2022) Comparison of single image HDR reconstruction methods - the caveats of quality assessment SIGGRAPH '22: ACM SIGGRAPH 2022 Conference Proceedings, p. 1-8, Article 1 (Conference paper) Continue to DOI

2021

Gabriel Eilertsen, Saghi Hajisharif, Param Hanji, Apostolia Tsirikoglou, Rafal K. Mantiuk, Jonas Unger (2021) How to cheat with metrics in single-image HDR reconstruction 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021), p. 3981-3990 (Conference paper) Continue to DOI

Research

Organisation