DIAR: Deep Image Alignment and Reconstruction using Swin Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwiatkowski, Monika, Matern, Simon, Hellwich, Olaf
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914801279565824
author Kwiatkowski, Monika
Matern, Simon
Hellwich, Olaf
author_facet Kwiatkowski, Monika
Matern, Simon
Hellwich, Olaf
contents When taking images of some occluded content, one is often faced with the problem that every individual image frame contains unwanted artifacts, but a collection of images contains all relevant information if properly aligned and aggregated. In this paper, we attempt to build a deep learning pipeline that simultaneously aligns a sequence of distorted images and reconstructs them. We create a dataset that contains images with image distortions, such as lighting, specularities, shadows, and occlusion. We create perspective distortions with corresponding ground-truth homographies as labels. We use our dataset to train Swin transformer models to analyze sequential image data. The attention maps enable the model to detect relevant image content and differentiate it from outliers and artifacts. We further explore using neural feature maps as alternatives to classical key point detectors. The feature maps of trained convolutional layers provide dense image descriptors that can be used to find point correspondences between images. We utilize this to compute coarse image alignments and explore its limitations.
format Preprint
id arxiv_https___arxiv_org_abs_2310_11605
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DIAR: Deep Image Alignment and Reconstruction using Swin Transformers
Kwiatkowski, Monika
Matern, Simon
Hellwich, Olaf
Computer Vision and Pattern Recognition
Machine Learning
When taking images of some occluded content, one is often faced with the problem that every individual image frame contains unwanted artifacts, but a collection of images contains all relevant information if properly aligned and aggregated. In this paper, we attempt to build a deep learning pipeline that simultaneously aligns a sequence of distorted images and reconstructs them. We create a dataset that contains images with image distortions, such as lighting, specularities, shadows, and occlusion. We create perspective distortions with corresponding ground-truth homographies as labels. We use our dataset to train Swin transformer models to analyze sequential image data. The attention maps enable the model to detect relevant image content and differentiate it from outliers and artifacts. We further explore using neural feature maps as alternatives to classical key point detectors. The feature maps of trained convolutional layers provide dense image descriptors that can be used to find point correspondences between images. We utilize this to compute coarse image alignments and explore its limitations.
title DIAR: Deep Image Alignment and Reconstruction using Swin Transformers
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2310.11605