Related papers: GeoLink: A 3D-Aware Framework Towards Better Gener…
Cross-view localization and synthesis are two fundamental tasks in cross-view visual understanding, which deals with cross-view datasets: overhead (satellite or aerial) and ground-level imagery. These tasks have gained increasing attention…
Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations.…
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…
Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations, current methods rely solely on 2D visual cues to establish…
We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images capturing semantically similar objects. Given a collection of unlabeled Internet images, our goal is to associate the shared semantic parts from the inputs and…
Deep learning techniques for point clouds have achieved strong performance on a range of 3D vision tasks. However, it is costly to annotate large-scale point sets, making it critical to learn generalizable representations that can transfer…
3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer…
Unsupervised Domain Adaptation has been an efficient approach to transferring the semantic segmentation model across data distributions. Meanwhile, the recent Open-vocabulary Semantic Scene understanding based on large-scale vision language…
Determining the precise geographic location of an image at a global scale remains an unsolved challenge. Standard image retrieval techniques are inefficient due to the sheer volume of images (>100M) and fail when coverage is insufficient.…
Vision-Language-Action (VLA) models achieve strong generalization in robotic manipulation but remain largely reactive and 2D-centric, making them unreliable in tasks that require precise 3D reasoning. We propose GeoPredict, a geometry-aware…
Developing gaze estimation models that generalize well to unseen domains and in-the-wild conditions remains a challenge with no known best solution. This is mostly due to the difficulty of acquiring ground truth data that cover the…
This paper addresses the problem of cross-view image geo-localization, where the geographic location of a ground-level street-view query image is estimated by matching it against a large scale aerial map (e.g., a high-resolution satellite…
Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision, especially when the input views have little or no overlap. In such cases, existing…
Cross-view geo-localization identifies the locations of street-view images by matching them with geo-tagged satellite images or OSM. However, most existing studies focus on image-to-image retrieval, with fewer addressing text-guided…
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding…
Although various visual localization approaches exist, such as scene coordinate regression and camera pose regression, these methods often struggle with optimization complexity or limited accuracy. To address these challenges, we explore…
We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between…
In this work, we aim at an important but less explored problem of a simple yet effective backbone specific for cross-view geo-localization task. Existing methods for cross-view geo-localization tasks are frequently characterized by 1)…
The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not…
The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…