Mask-guided Style Transfer Network for Purifying Real Images

03/19/2019
by   Tongtong Zhao, et al.
0

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images compared with real images, the desired performance cannot be achieved. To solve this problem, the previous method learned a model to improve the realism of the synthetic images. Different from the previous methods, this paper try to purify real image by extracting discriminative and robust features to convert outdoor real images to indoor synthetic images. In this paper, we first introduce the segmentation masks to construct RGB-mask pairs as inputs, then we design a mask-guided style transfer network to learn style features separately from the attention and bkgd(background) regions and learn content features from full and attention region. Moreover, we propose a novel region-level task-guided loss to restrain the features learnt from style and content. Experiments were performed using mixed studies (qualitative and quantitative) methods to demonstrate the possibility of purifying real images in complex directions. We evaluate the proposed method on various public datasets, including LPW, COCO and MPIIGaze. Experimental results show that the proposed method is effective and achieves the state-of-the-art results.

READ FULL TEXT
research
03/14/2019

Purifying Naturalistic Images through a Real-time Style Transfer Semantics Network

Recently, the progress of learning-by-synthesis has proposed a training ...
research
05/27/2020

Arbitrary Style Transfer via Multi-Adaptation Network

Arbitrary style transfer is a significant topic with both research value...
research
10/08/2018

Guiding Intelligent Surveillance System by learning-by-synthesis gaze estimation

We describe a novel learning-by-synthesis method for estimating gaze dir...
research
11/07/2021

Style Transfer with Target Feature Palette and Attention Coloring

Style transfer has attracted a lot of attentions, as it can change a giv...
research
01/06/2022

Consistent Style Transfer

Recently, attentional arbitrary style transfer methods have been propose...
research
08/17/2023

SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow Detection

Despite significant progress in shadow detection, current methods still ...
research
08/12/2020

Look here! A parametric learning based approach to redirect visual attention

Across photography, marketing, and website design, being able to direct ...

Please sign up or login with your details

Forgot password? Click here to reset