Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow

03/30/2021
by   Shangrong Yang, et al.
0

Distortion rectification is often required for fisheye images. The generation-based method is one mainstream solution due to its label-free property, but its naive skip-connection and overburdened decoder will cause blur and incomplete correction. First, the skip-connection directly transfers the image features, which may introduce distortion and cause incomplete correction. Second, the decoder is overburdened during simultaneously reconstructing the content and structure of the image, resulting in vague performance. To solve these two problems, in this paper, we focus on the interpretable correction mechanism of the distortion rectification network and propose a feature-level correction scheme. We embed a correction layer in skip-connection and leverage the appearance flows in different layers to pre-correct the image features. Consequently, the decoder can easily reconstruct a plausible result with the remaining distortion-less information. In addition, we propose a parallel complementary structure. It effectively reduces the burden of the decoder by separating content reconstruction and structure correction. Subjective and objective experiment results on different datasets demonstrate the superiority of our method.

READ FULL TEXT

page 3

page 4

page 5

page 6

page 7

page 8

research
02/08/2023

Spatiotemporal Deformation Perception for Fisheye Video Rectification

Although the distortion correction of fisheye images has been extensivel...
research
09/08/2019

Blind Geometric Distortion Correction on Images Through Deep Learning

We propose the first general framework to automatically correct differen...
research
10/25/2019

ClsGAN: Selective Attribute Editing Based On Classification Adversarial Network

Attribution editing has shown remarking progress by the incorporating of...
research
08/13/2021

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

In this paper, we propose a photorealistic style transfer network to emp...
research
01/11/2020

Symmetric Skip Connection Wasserstein GAN for High-Resolution Facial Image Inpainting

We propose a Symmetric Skip Connection Wasserstein Generative Adversaria...
research
10/30/2016

Real-Time Image Distortion Correction: Analysis and Evaluation of FPGA-Compatible Algorithms

Image distortion correction is a critical pre-processing step for a vari...
research
06/07/2023

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT

Nonuniform rotational distortion (NURD) correction is vital for endoscop...

Please sign up or login with your details

Forgot password? Click here to reset