Adaptive Image Inpainting

01/01/2022
by   Maitreya Suin, et al.
1

Image inpainting methods have shown significant improvements by using deep neural networks recently. However, many of these techniques often create distorted structures or blurry textures inconsistent with surrounding areas. The problem is rooted in the encoder layers' ineffectiveness in building a complete and faithful embedding of the missing regions. To address this problem, two-stage approaches deploy two separate networks for a coarse and fine estimate of the inpainted image. Some approaches utilize handcrafted features like edges or contours to guide the reconstruction process. These methods suffer from huge computational overheads owing to multiple generator networks, limited ability of handcrafted features, and sub-optimal utilization of the information present in the ground truth. Motivated by these observations, we propose a distillation based approach for inpainting, where we provide direct feature level supervision for the encoder layers in an adaptive manner. We deploy cross and self distillation techniques and discuss the need for a dedicated completion-block in encoder to achieve the distillation target. We conduct extensive evaluations on multiple datasets to validate our method.

READ FULL TEXT
research
12/08/2020

Texture Transform Attention for Realistic Image Inpainting

Over the last few years, the performance of inpainting to fill missing r...
research
08/11/2019

StructureFlow: Image Inpainting via Structure-aware Appearance Flow

Image inpainting techniques have shown significant improvements by using...
research
01/24/2018

Generative Image Inpainting with Contextual Attention

Recent deep learning based approaches have shown promising results on im...
research
07/14/2020

Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations

Deep encoder-decoder based CNNs have advanced image inpainting methods f...
research
05/22/2019

PEPSI++: Fast and Lightweight Network for Image Inpainting

Generative adversarial network (GAN)-based image inpainting methods whic...
research
12/18/2019

One-Stage Inpainting with Bilateral Attention and Pyramid Filling Block

Recent deep learning based image inpainting methods which utilize contex...
research
01/29/2018

Shift-Net: Image Inpainting via Deep Feature Rearrangement

Deep convolutional networks (CNNs) have exhibited their potential in ima...

Please sign up or login with your details

Forgot password? Click here to reset