Authors:
Monika Kwiatkowski
;
Simon Matern
and
Olaf Hellwich
Affiliation:
Computer Vision & Remote Sensing, Technische Universität Berlin, Marchstr. 23, Berlin, Germany
Keyword(s):
Synthetic Dataset, Image Alignment, Homography Estimation, Dense Correspondences, Image Restoration, Shadow Removal, Background Subtraction, Descriptor Learning.
Abstract:
In this paper, we present a synthetic dataset generation to create large-scale datasets for various image restoration and registration tasks. Illumination changes, shadows, occlusions, and perspective distortions are added to a given image using a 3D rendering pipeline. Each sequence contains the undistorted image, occlusion masks, and homographies. Although we provide two specific datasets, the data generation itself can be customized and used to generate an arbitrarily large dataset with an arbitrary combination of distortions. The datasets allow end-to-end training of deep learning methods for tasks such as image restoration, background subtraction, image matching, and homography estimation. We evaluate multiple image restoration methods to reconstruct the content from a sequence of distorted images. Additionally, a benchmark is provided that evaluates keypoint detectors and image matching methods. Our evaluations show that even learned image descriptors struggle to identify and m
atch keypoints under varying lighting conditions.
(More)