An official website of the United States government
Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and different capturing time between two views. Despite these difficulties, recent works achieve outstanding progress on cross-view geo-localization benchmarks. However, existing methods still suffer from poor performance on the cross-area benchmarks, in which the training and testing data are captured from two different regions. We attribute this deficiency to the lack of ability to extract the spatial configuration of visual feature layouts and models' overfitting on low-level details from the training set. In this paper, we propose GeoDTR which explicitly disentangles geometric information from raw features and learns the spatial correlations among visual features from aerial and ground pairs with a novel geometric layout extractor module. This module generates a set of geometric layout descriptors, modulating the raw features and producing high-quality latent representations. In addition, we elaborate on two categories of data augmentations, (i) Layout simulation, which varies the spatial configuration while keeping the low-level details intact. (ii) Semantic augmentation, which alters the low-level details and encourages the model to capture spatial configurations. These augmentations help to improve the performance of the cross-view geo-localization models, especially on the cross-area benchmarks. Moreover, we propose a counterfactual-based learning process to benefit the geometric layout extractor in exploring spatial information. Extensive experiments show that GeoDTR not only achieves state-of-the-art results but also significantly boosts the performance on same-area and cross-area benchmarks. Our code can be found at https://gitlab.com/vail-uvm/geodtr.
more »
« less
View Synthesis with Scene Recognition for Cross-View Image Localization
Image-based localization has been widely used for autonomous vehicles, robotics, augmented reality, etc., and this is carried out by matching a query image taken from a cell phone or vehicle dashcam to a large scale of geo-tagged reference images, such as satellite/aerial images or Google Street Views. However, the problem remains challenging due to the inconsistency between the query images and the large-scale reference datasets regarding various light and weather conditions. To tackle this issue, this work proposes a novel view synthesis framework equipped with deep generative models, which can merge the unique features from the outdated reference dataset with features from the images containing seasonal changes. Our design features a unique scheme to ensure that the synthesized images contain the important features from both reference and patch images, covering seasonable features and minimizing the gap for the image-based localization tasks. The performance evaluation shows that the proposed framework can synthesize the views in various weather and lighting conditions.
more »
« less
- Award ID(s):
- 1950704
- PAR ID:
- 10493347
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Future Internet
- Volume:
- 15
- Issue:
- 4
- ISSN:
- 1999-5903
- Page Range / eLocation ID:
- 126
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Vision-based localization approaches now underpin newly emerging navigation pipelines for myriad use cases, from robotics to assistive technologies. Compared to sensor-based solutions, vision-based localization does not require pre-installed sensor infrastructure, which is costly, time-consuming, and/or often infeasible at scale. Herein, we propose a novel vision-based localization pipeline for a specific use case: navigation support for end users with blindness and low vision. Given a query image taken by an end user on a mobile application, the pipeline leverages a visual place recognition (VPR) algorithm to find similar images in a reference image database of the target space. The geolocations of these similar images are utilized in a downstream task that employs a weighted-average method to estimate the end user’s location. Another downstream task utilizes the perspective-n-point (PnP) algorithm to estimate the end user’s direction by exploiting the 2D–3D point correspondences between the query image and the 3D environment, as extracted from matched images in the database. Additionally, this system implements Dijkstra’s algorithm to calculate a shortest path based on a navigable map that includes the trip origin and destination. The topometric map used for localization and navigation is built using a customized graphical user interface that projects a 3D reconstructed sparse map, built from a sequence of images, to the corresponding a priori 2D floor plan. Sequential images used for map construction can be collected in a pre-mapping step or scavenged through public databases/citizen science. The end-to-end system can be installed on any internet-accessible device with a camera that hosts a custom mobile application. For evaluation purposes, mapping and localization were tested in a complex hospital environment. The evaluation results demonstrate that our system can achieve localization with an average error of less than 1 m without knowledge of the camera’s intrinsic parameters, such as focal length.more » « less
-
null (Ed.)The success of supervised learning requires large-scale ground truth labels which are very expensive, time- consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks including multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method.more » « less
-
With the ever-increasing amount of 3D data being captured and processed, multi-view image compression is essential to various applications, including virtual reality and 3D modeling. Despite the considerable success of learning-based compression models on single images, limited progress has been made in multi-view image compression. In this paper, we propose an efficient approach to multi-view image compression by leveraging the redundant information across different viewpoints without explicitly using warping operations or camera parameters. Our method builds upon the recent advancements in Multi-Reference Entropy Models (MEM), which were initially proposed to capture correlations within an image. We extend the MEM models to employ cross-view correlations in addition to within-image correlations. Specifically, we generate latent representations for each view independently and integrate a cross-view context module within the entropy model. The estimation of entropy parameters for each view follows an autoregressive technique, leveraging correlations with the previous views. We show that adding this view context module further enhances the compression performance when jointly trained with the autoencoder. Experimental results demonstrate superior performance compared to both traditional and learning-based multi-view compression methods.more » « less
-
In recent years, novel view synthesis from a single image has seen significant progress thanks to the rapid advancements in 3D scene representation and image inpainting techniques. While the current approaches are able to synthesize geometrically consistent novel views, they often do not handle the view-dependent effects properly. Specifically, the highlights in their synthesized images usually appear to be glued to the surfaces, making the novel views unrealistic. To address this major problem, we make a key observation that the process of synthesizing novel views requires changing the shading of the pixels based on the novel camera, and moving them to appropriate locations. Therefore, we propose to split the view synthesis process into two independent tasks of pixel reshading and relocation. During the reshading process, we take the single image as the input and adjust its shading based on the novel camera. This reshaded image is then used as the input to an existing view synthesis method to relocate the pixels and produce the final novel view image. We propose to use a neural network to perform reshading and generate a large set of synthetic input-reshaded pairs to train our network. We demonstrate that our approach produces plausible novel view images with realistic moving highlights on a variety of real world scenes.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/fi15040126
