Multi-Level Generative Chaotic Recurrent Network for Image Inpainting

A. Lynn Abbott

Abstract

This paper presents a novel multi-level generative chaotic Recurrent Neural Network (RNN) for image inpainting. This technique utilizes a general framework with multiple chaotic RNN that makes learning the image prior from a single corrupted image more robust and efficient. The proposed network utilizes a randomly-initialized process for parameterization, along with a unique quad-directional encoder structure, chaotic state transition, and adaptive importance for multi-level RNN updating. The efficacy of the approach has been validated through multiple experiments. In spite of a much lower computational load, quantitative comparisons reveal that the proposed approach exceeds the performance of several image-restoration benchmarks.

Cong Chen, Amos Lynn Abbott, Daniel J. Stilwell: Multi-Level Generative Chaotic Recurrent Network for Image Inpainting. WACV 2021: 3625-3634