DeepAI AI Chat
Log In Sign Up

Thermal Infrared Image Inpainting via Edge-Aware Guidance

10/28/2022
by   Zeyu Wang, et al.
Zhejiang University
0

Image inpainting has achieved fundamental advances with deep learning. However, almost all existing inpainting methods aim to process natural images, while few target Thermal Infrared (TIR) images, which have widespread applications. When applied to TIR images, conventional inpainting methods usually generate distorted or blurry content. In this paper, we propose a novel task – Thermal Infrared Image Inpainting, which aims to reconstruct missing regions of TIR images. Crucially, we propose a novel deep-learning-based model TIR-Fill. We adopt the edge generator to complete the canny edges of broken TIR images. The completed edges are projected to the normalization weights and biases to enhance edge awareness of the model. In addition, a refinement network based on gated convolution is employed to improve TIR image consistency. The experiments demonstrate that our method outperforms state-of-the-art image inpainting approaches on FLIR thermal dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/01/2019

EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning

Over the last few years, deep learning techniques have yielded significa...
11/03/2019

Image Inpainting by Adaptive Fusion of Variable Spline Interpolations

There are many methods for image enhancement. Image inpainting is one of...
12/01/2018

Deep Inception Generative Network for Cognitive Image Inpainting

Recent advances in deep learning have shown exciting promise in filling ...
01/17/2018

Light-weight pixel context encoders for image inpainting

In this work we propose Pixel Content Encoders (PCE), a light-weight ima...
05/08/2022

Iterative Geometry-Aware Cross Guidance Network for Stereo Image Inpainting

Currently, single image inpainting has achieved promising results based ...
10/29/2020

Free-Form Image Inpainting via Contrastive Attention Network

Most deep learning based image inpainting approaches adopt autoencoder o...