DeepAI AI Chat
Log In Sign Up

Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs

by   Jenny Schmalfuss, et al.
University of Stuttgart
University of Houston

Blind inpainting algorithms based on deep learning architectures have shown a remarkable performance in recent years, typically outperforming model-based methods both in terms of image quality and run time. However, neural network strategies typically lack a theoretical explanation, which contrasts with the well-understood theory underlying model-based methods. In this work, we leverage the advantages of both approaches by integrating theoretically founded concepts from transform domain methods and sparse approximations into a CNN-based approach for blind image inpainting. To this end, we present a novel strategy to learn convolutional kernels that applies a specifically designed filter dictionary whose elements are linearly combined with trainable weights. Numerical experiments demonstrate the competitiveness of this approach. Our results show not only an improved inpainting quality compared to conventional CNNs but also significantly faster network convergence within a lightweight network design.


page 2

page 9

page 10

page 11

page 14


An Algorithm Unrolling Approach to Deep Blind Image Deblurring

Blind image deblurring remains a topic of enduring interest. Learning ba...

Multi-scale Sparse Representation-Based Shadow Inpainting for Retinal OCT Images

Inpainting shadowed regions cast by superficial blood vessels in retinal...

Learning Energy Based Inpainting for Optical Flow

Modern optical flow methods are often composed of a cascade of many inde...

Perceptually Motivated Method for Image Inpainting Comparison

The field of automatic image inpainting has progressed rapidly in recent...

PEPSI++: Fast and Lightweight Network for Image Inpainting

Generative adversarial network (GAN)-based image inpainting methods whic...

View Blind-spot as Inpainting: Self-Supervised Denoising with Mask Guided Residual Convolution

In recent years, self-supervised denoising methods have shown impressive...

Enhancement of damaged-image prediction through Cahn-Hilliard Image Inpainting

We assess the benefit of including an image inpainting filter before pas...