1 code implementation • 16 Aug 2023 • Alnur Alimanov, Md Baharul Islam
We developed a Retinal Trees (ReTree) dataset consisting of retinal images, corresponding vessel trees, and a segmentation network based on DDPM trained with images from the ReTree dataset.
1 code implementation • 18 Apr 2023 • Hassan Imani, Md Baharul Islam, Lai-Kuan Wong
We use 1D convolution for shifting the salient objects and design a stereo video Transformer to assist the retargeting process.
1 code implementation • 3 Mar 2023 • Alnur Alimanov, Md Baharul Islam
It consists of two generators that translate images from one domain to another (e. g., low- to high-quality and vice versa), playing an adversarial game with two discriminators.
1 code implementation • 19 Sep 2022 • Md Imran Hosen, Md Baharul Islam
Inspired by the recent image inpainting methods, we propose an end-to-end hybrid masked face recognition system, namely HiMFR, consisting of three significant parts: masked face detector, face inpainting, and face recognition.
1 code implementation • 19 Sep 2022 • Md Imran Hosen, Md Baharul Islam
Realistic image restoration with high texture areas such as removing face masks is challenging.
2 code implementations • 9 Sep 2022 • Alnur Alimanov, Md Baharul Islam
The retinal vessel segmentation performance was compared with the ground-truth fundus images.
1 code implementation • 21 Apr 2022 • Hassan Imani, Md Baharul Islam, Lai-Kuan Wong
Due to the lack of a benchmark dataset suitable for the SVSR task, we collected a new stereoscopic video dataset, SVSR-Set, containing 71 full high-definition (HD) stereo videos captured using a professional stereo camera.
no code implementations • 21 Apr 2022 • Masum Shah Junayed, Afsana Ahsan Jeny, Md Baharul Islam, Ikhtiar Ahmed, A F M Shahen Shah
For ILDs pattern classification, the proposed approach achieved the accuracy scores of 99. 09% and the average F score of 97. 9%, outperforming three pre-trained CNNs.
no code implementations • 11 Apr 2022 • Masum Shah Junayed, Arezoo Sadeghzadeh, Md Baharul Islam, Lai-Kuan Wong, Tarkan Aydin
Extensive experiments conducted on three datasets; Stanford3D, Matterport3D, and SunCG, demonstrate that HiMODE can achieve state-of-the-art performance for 360{\deg} monocular depth estimation.
Ranked #1 on Depth Estimation on Stanford2D3D Panoramic