DeepAI AI Chat
Log In Sign Up

Patch-wise Contrastive Style Learning for Instagram Filter Removal

by   Furkan Kınlı, et al.

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.


page 2

page 4

page 6

page 7


Instagram Filter Removal on Fashionable Images

Social media images are generally transformed by filtering to obtain aes...

AIM 2022 Challenge on Instagram Filter Removal: Methods and Results

This paper introduces the methods and the results of AIM 2022 challenge ...

Language-Driven Image Style Transfer

Despite having promising results, style transfer, which requires prepari...

StyTr^2: Unbiased Image Style Transfer with Transformers

The goal of image style transfer is to render an image with artistic fea...

Few-shot Font Generation by Learning Style Difference and Similarity

Few-shot font generation (FFG) aims to preserve the underlying global st...

Reversing Image Signal Processors by Reverse Style Transferring

RAW image datasets are more suitable than the standard RGB image dataset...