MedDeblur: Medical Image Deblurring with Residual Dense Spatial-Asymmetric Attention

1 code implementation • Mathematics 2022 • S. M. A. Sharif, Rizwan Ali Naqvi, Zahid Mehmood, Jamil Hussain, Ahsan Ali, Seung-Won Lee

The performance of the proposed methods has been densely evaluated and compared with the existing deblurring methods.

Deblurring Image Deblurring +1

AIM 2022 Challenge on Instagram Filter Removal: Methods and Results

1 code implementation • 17 Oct 2022 • Furkan Kınlı, Sami Menteş, Barış Özcan, Furkan Kıraç, Radu Timofte, Yi Zuo, Zitao Wang, Xiaowen Zhang, Yu Zhu, Chenghua Li, Cong Leng, Jian Cheng, Shuai Liu, Chaoyu Feng, Furui Bai, Xiaotao Wang, Lei Lei, Tianzhi Ma, Zihan Gao, Wenxin He, Woon-Ha Yeo, Wang-Taek Oh, Young-Il Kim, Han-Cheol Ryu, Gang He, Shaoyi Long, S. M. A. Sharif, Rizwan Ali Naqvi, Sungjun Kim, Guisik Kim, Seohyeon Lee, Sabari Nathan, Priya Kansal

This paper introduces the methods and the results of AIM 2022 challenge on Instagram Filter Removal.

SAGAN: Adversarial Spatial-asymmetric Attention for Noisy Nona-Bayer Reconstruction

1 code implementation • The British Machine Vision Conference 2021 • S M A Sharif, Rizwan Ali Naqvi, Mithun Biswas

We combine our proposed module with adversarial learning to produce plausible images from Nona-Bayer CFA.

Image Reconstruction Joint Demosaicing and Denoising

Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor

1 code implementation • 19 Apr 2021 • SMA Sharif, Rizwan Ali Naqvi, Mithun Biswas

In this paper, we tackle the challenges of joint demosaicing and denoising (JDD) on such an image sensor by introducing a novel learning-based method.

Demosaicking Denoising +1

A Two-stage Deep Network for High Dynamic Range Image Reconstruction

1 code implementation • 19 Apr 2021 • SMA Sharif, Rizwan Ali Naqvi, Mithun Biswas, Kim Sungjun

Notably, our proposed method aims to reconstruct an HDR image without knowing hardware information, including camera response function (CRF) and exposure settings.

Denoising Image Enhancement +7