no code implementations • 16 Nov 2021 • Milad Niknejad, Alexandre Bernardino
Fire localization in images and videos is an important step for an autonomous system to combat fire incidents.
no code implementations • 4 Nov 2021 • Milad Niknejad, Alexandre Bernardino
The network is jointly trained for both segmentation and classification, leading to improvement in the performance of the single-task image segmentation methods, and the previous methods proposed for fire segmentation.
no code implementations • 9 Jul 2018 • Milad Niknejad, Jose M. Bioucas-Dias, Mario A. T. Figueiredo
This paper proposes a general framework for internal patch-based image restoration based on Conditional Random Fields (CRF).
no code implementations • 9 Jul 2018 • Milad Niknejad, Jose M. Bioucas-Dias, Mario A. T. Figueiredo
This paper introduces a new approach to patch-based image restoration based on external datasets and importance sampling.
no code implementations • 1 Mar 2018 • Milad Niknejad, Mario A. T. Figueiredo
In this paper, we address the problem of denoising images degraded by Poisson noise.
no code implementations • 21 Jun 2017 • Milad Niknejad, Jose M. Bioucas-Dias, Mario A. T. Figueiredo
In this paper, we propose a new image denoising method, tailored to specific classes of images, assuming that a dataset of clean images of the same class is available.
no code implementations • 9 Jun 2017 • Milad Niknejad, Jose M. Bioucas-Dias, Mario A. T. Figueiredo
In this paper, we address the problem of recovering images degraded by Poisson noise, where the image is known to belong to a specific class.