Related papers: Geo$^\textbf{2}$: Geometry-Guided Cross-view Geo-L…
This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of…
The concept of geo-localization refers to the process of determining where on earth some `entity' is located, typically using Global Positioning System (GPS) coordinates. The entity of interest may be an image, sequence of images, a video,…
3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…
From a single image, visual cues can help deduce intrinsic and extrinsic camera parameters like the focal length and the gravity direction. This single-image calibration can benefit various downstream applications like image editing and 3D…
Multimodal Large Language Models (MLLMs) demonstrate exceptional semantic reasoning but struggle with 3D spatial perception when restricted to pure RGB inputs. Despite leveraging implicit geometric priors from 3D reconstruction models,…
Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent…
Cross-view geo-localization (CVGL) aims to accurately localize street-view images through retrieval of corresponding geo-tagged satellite images. While prior works have achieved nearly perfect performance on certain standard datasets, their…
Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large…
We address the problem of ground-to-satellite image geo-localization, that is, estimating the camera latitude, longitude and orientation (azimuth angle) by matching a query image captured at the ground level against a large-scale database…
Cross-view localization aims to estimate the 3-DoF pose of a ground-view image by aligning it with aerial or satellite imagery. Existing methods typically address this task through direct regression or feature alignment in a shared…
Cross-view geo-localization confronts significant challenges due to large perspective changes, especially when the ground-view query image has a limited field of view with unknown orientation. To bridge the cross-view domain gap, we for the…
Improving and homogenizing time and space reference systems on Earth and, more directly, realizing the Terrestrial Reference Frame (TRF) with an accuracy of 1mm and a long-term stability of 0.1mm/year are relevant for many scientific and…
Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In this work, instead of pinhole and satellite images, we study robust MCVGL using holistic…
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies…
Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the input views are extremely sparse. To address this issue, we…
Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in geo-localization…
Large-scale pretraining on Earth observation imagery has yielded powerful representations of the natural and built environment. However, most existing geospatial foundation models do not directly model the structured socioeconomic…
Recently, Gaussian Splatting (GS) has shown great potential for urban scene reconstruction in the field of autonomous driving. However, current urban scene reconstruction methods often depend on multimodal sensors as inputs, \textit{i.e.}…
We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image…
Monocular 3D hand reconstruction is intrinsically a geometric problem, yet RGB appearance features alone often struggle to resolve severe ambiguities caused by self-occlusions and hand-object interactions. While introducing depth can…