Browsing Computer Science by OzU Authors "Kınlı, Osman Furkan"
Now showing items 1-12 of 12
-
AIM 2022 challenge on instagram filter removal: Methods and results
Kınlı, Osman Furkan; Menteş, Sami; Özcan, Barış; Kıraç, Mustafa Furkan (Springer, 2023)This paper introduces the methods and the results of AIM 2022 challenge on Instagram Filter Removal. Social media filters transform the images by consecutive non-linear operations, and the feature maps of the original ... -
A benchmark for inpainting of clothing images with irregular holes
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (Springer, 2020)Fashion image understanding is an active research field with a large number of practical applications for the industry. Despite its practical impacts on intelligent fashion analysis systems, clothing image inpainting has ... -
Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (The ACM Digital Library, 2020-04-14)Inpainting a particular missing region in an image is a challenging vision task, and promising improvements on this task have been achieved with the help of the recent developments in vision-related deep learning studies. ... -
Deterministic neural illumination mapping for efficient auto-white balance correction
Kınlı, Osman Furkan; Yılmaz, Doğa; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2023)Auto-white balance (AWB) correction is a critical operation in image signal processors for accurate and consistent color correction across various illumination scenarios. This paper presents a novel and efficient AWB ... -
Fashion image retrieval with capsule networks
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2019)In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two ... -
Generalization to unseen viewpoint images of objects via alleviated pose attentive capsule agreement
Özcan, Barış; Kınlı, Osman Furkan; Kıraç, Mustafa Furkan (Springer, 2023-02)Despite their achievements in object recognition, Convolutional Neural Networks (CNNs) particularly fail to generalize to unseen viewpoints of a learned object even with substantial samples. On the other hand, recently ... -
Instagram filter removal on fashionable images
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2021-06)Social media images are generally transformed by filtering to obtain aesthetically more pleasing appearances. However, CNNs generally fail to interpret both the image and its filtered version as the same in the visual ... -
Modeling the lighting in scenes as style for auto white-balance correction
Kınlı, Osman Furkan; Yılmaz, Doğa; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2023)Style may refer to different concepts (e.g. painting style, hairstyle, texture, color, filter, etc.) depending on how the feature space is formed. In this work, we propose a novel idea of interpreting the lighting in the ... -
NTIRE 2023 challenge on night photography rendering
Shutova, A.; Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2023)This paper presents a review of the NTIRE 2023 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions conditions, and thereby ... -
Patch-wise contrastive style learning for instagram filter removal
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2022)Image-level corruptions and perturbations degrade the performance of CNNs on different downstream vision tasks. Social media filters are one of the most common resources of various corruptions and perturbations for real-world ... -
Quaternion capsule networks
Özcan, Barış; Kınlı, Osman Furkan (IEEE, 2021)Capsules are grouping of neurons that allow to represent sophisticated information of a visual entity such as pose and features. In the view of this property, Capsule Networks outperform CNNs in challenging tasks like ... -
Reversing image signal processors by reverse style transferring
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (Springer, 2023)RAW image datasets are more suitable than the standard RGB image datasets for the ill-posed inverse problems in low-level vision, but not common in the literature. There are also a few studies to focus on mapping sRGB ...
Share this page
