An official website of the United States government
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a novel view synthesis framework equipped with deep generative models, which can merge the unique features from the outdated reference dataset with features from the images containing seasonal changes.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
Cross-View Geo-Localization via Learning Disentangled Geometric Layout Correspondence
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
- Award ID(s):
- 2218063
- PAR ID:
- 10515037
- Publisher / Repository:
- AAAI
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 37
- Issue:
- 3
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 3480 to 3488
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Unmanned aerial vehicles (UAVs) must keep track of their location in order to maintain flight plans. Currently, this task is almost entirely performed by a combination of Inertial Measurement Units (IMUs) and reference to GNSS (Global Navigation Satellite System). Navigation by GNSS, however, is not always reliable, due to various causes both natural (reflection and blockage from objects, technical fault, inclement weather) and artificial (GPS spoofing and denial). In such GPS-denied situations, it is desirable to have additional methods for aerial geolocalization. One such method is visual geolocalization, where aircraft use their ground facing cameras to localize and navigate. The state of the art in many ground-level image processing tasks involve the use of Convolutional Neural Networks (CNNs). We present here a study of how effectively a modern CNN designed for visual classification can be applied to the problem of Absolute Visual Geolocalization (AVL, localization without a prior location estimate). An Xception based architecture is trained from scratch over a >1000 km2 section of Washington County, Arkansas to directly regress latitude and longitude from images from different orthorectified high-altitude survey flights. It achieves average localization accuracy on unseen image sets over the same region from different years and seasons with as low as 115 m average error, which localizes to 0.004% of the training area, or about 8% of the width of the 1.5 × 1.5 km input image. This demonstrates that CNNs are expressive enough to encode robust landscape information for geolocalization over large geographic areas. Furthermore, discussed are methods of providing uncertainty for CNN regression outputs, and future areas of potential improvement for use of deep neural networks in visual geolocalization.more » « less
-
We investigate exocentric-to-egocentric cross-view translation, which aims to generate a first-person (egocentric) view of an actor based on a video recording that captures the actor from a third-person (exocentric) perspective. To this end, we propose a generative framework called Exo2Ego that decouples the translation process into two stages: high-level structure transformation, which explicitly encourages cross-view correspondence between exocentric and egocentric views, and a diffusion-based pixel-level hallucination, which incorporates a hand layout prior to enhance the fidelity of the generated egocentric view. To pave the way for future advancements in this field, we curate a comprehensive exo-to-ego cross-view translation benchmark. It consists of a diverse collection of synchronized ego-exo tabletop activity video pairs sourced from three public datasets: H2O, Aria Pilot, and Assembly101. The experimental results validate that Exo2Ego delivers photorealistic video results with clear hand manipulation details and outperforms several baselines in terms of both synthesis quality and generalization ability to new actions.more » « less
-
Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust evaluation methods to assess these capabilities. We introduce TurtleBench, a benchmark designed to evaluate LMMs’ capacity to interpret geometric patterns—given visual examples, textual instructions, or both—and generate precise code outputs. Inspired by turtle geometry, a notion used to teach children foundational coding and geometric concepts, TurtleBench features tasks with patterned shapes that have underlying algorithmic logic. Our evaluation reveals that leading LMMs struggle significantly with these tasks, with GPT-4V achieving only 19% accuracy on the simplest tasks and few-shot prompting only marginally improves their performance (<2%). TurtleBench highlights the gap between human and AI performance in intuitive and visual geometrical understanding, setting the stage for future research in this area and stands as one of the few benchmarks to evaluate the integration of visual understanding and code generation capabilities in LMMs, setting the stage for future research.more » « less
-
With the increase of multi-view graph data, multi-view graph clustering (MVGC) that can discover the hidden clusters without label supervision has attracted growing attention from researchers. Existing MVGC methods are often sensitive to the given graphs, especially influenced by the low quality graphs, i.e., they tend to be limited by the homophily assumption. However, the widespread real-world data hardly satisfy the homophily assumption. This gap limits the performance of existing MVGC methods on low homophilous graphs. To mitigate this limitation, our motivation is to extract high-level view-common information which is used to refine each view's graph, and reduce the influence of non-homophilous edges. To this end, we propose dual label-guided graph refinement for multi-view graph clustering (DuaLGR), to alleviate the vulnerability in facing low homophilous graphs. Specifically, DuaLGR consists of two modules named dual label-guided graph refinement module and graph encoder module. The first module is designed to extract the soft label from node features and graphs, and then learn a refinement matrix. In cooperation with the pseudo label from the second module, these graphs are refined and aggregated adaptively with different orders. Subsequently, a consensus graph can be generated in the guidance of the pseudo label. Finally, the graph encoder module encodes the consensus graph along with node features to produce the high-level pseudo label for iteratively clustering. The experimental results show the superior performance on coping with low homophilous graph data. The source code for DuaLGR is available at https://github.com/YwL-zhufeng/DuaLGR.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1609/aaai.v37i3.25457
