paper-with-me

Papers

Patch-wise Contrastive Style Learning for Instagram Filter Removal

2022-04-15 · Furkan Kınlı, Barış Özcan, Furkan Kıraç

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 visual analysis applications. The negative effects of these distractive factors can be alleviated by recovering the original images with their pure style for the inference of the downstream vision tasks. Assuming these filters substantially inject a piece of additional style information to the social media images, we can formulate the problem of recovering the original versions as a reverse style transfer problem. We introduce Contrastive Instagram Filter Removal Network (CIFR), which enhances this idea for Instagram filter removal by employing a novel multi-layer patch-wise contrastive style learning mechanism. Experiments show our proposed strategy produces better qualitative and quantitative results than the previous studies. Moreover, we present the results of our additional experiments for proposed architecture within different settings. Finally, we present the inference outputs and quantitative comparison of filtered and recovered images on localization and segmentation tasks to encourage the main motivation for this problem.

📄 PDF Abstract BibTeX arXiv:2204.07486

Code (1)

birdortyedi/cifr-pytorch 공식 구현 pytorch

Tasks

Reverse Style TransferStyle Transfer

Similar Papers 제목 키워드 기반

Instagram Filter Removal on Fashionable Images

2021-04-11 · Furkan Kınlı, Barış Özcan, Furkan Kıraç

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 an…

Reverse Style TransferStyle Transfer

Recognizing Instagram Filtered Images with Feature De-stylization

2019-12-30 · Zhe Wu, Zuxuan Wu, Bharat Singh, Larry S. Davis

Deep neural networks have been shown to suffer from poor generalization when small perturbations are added (like Gaussian noise), yet little work has been done to evaluate their robustness to more natural image transform…

Style Transfer

Language-Driven Image Style Transfer

2021-06-01 · Tsu-Jui Fu, Xin Eric Wang, William Yang Wang

Despite having promising results, style transfer, which requires preparing style images in advance, may result in lack of creativity and accessibility. Following human instruction, on the other hand, is the most natural …

Style Transfer

Filter Style Transfer between Photos

2020-07-15 · ECCV 2020 8 · Jonghwa Yim, Jisung Yoo, Won-joon Do, Beomsu Kim 외

Over the past few years, image-to-image style transfer has risen to the frontiers of neural image processing. While conventional methods were successful in various tasks such as color and texture transfer between images,…

Image-to-Image TranslationStyle TransferTranslation

Spectral Normalization and Dual Contrastive Regularization for Image-to-Image Translation

2023-04-22 · Chen Zhao, Wei-Ling Cai, Zheng Yuan

Existing image-to-image (I2I) translation methods achieve state-of-the-art performance by incorporating the patch-wise contrastive learning into Generative Adversarial Networks. However, patch-wise contrastive learning o…

Contrastive LearningImage-to-Image TranslationTranslation