Related papers: GPA-VGGT:Adapting VGGT to Large Scale Localization…
Cross-View Geo-Localization (CVGL) involves determining the geographical location of a query image by matching it with a corresponding GPS-tagged reference image. Current state-of-the-art methods predominantly rely on training models with…
Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…
Feed-forward reconstruction has been progressed rapidly, with the Visual Geometry Grounded Transformer (VGGT) being a notable baseline. However, directly applying VGGT to autonomous driving (AD) fails to capture three domain-specific…
Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance…
We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e.g., camera poses, rigid transformations). Our…
Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly focus on policy design, they often neglect the structure and capacity of visual encoders, limiting…
General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., camera intrinsics, poses, and depth maps). To address this…
This paper investigates the effective utilization of unlabeled data for large-area cross-view geo-localization (CVGL), encompassing both unsupervised and semi-supervised settings. Common approaches to CVGL rely on ground-satellite image…
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…
Visual Geo-localization (VG) is a critical research area for identifying geo-locations from visual inputs, particularly in autonomous navigation for robotics and vehicles. Current VG methods often learn feature extractors from geo-labeled…
Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…
Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing…
Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural…
Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at…
In the last decade, supervised deep learning approaches have been extensively employed in visual odometry (VO) applications, which is not feasible in environments where labelled data is not abundant. On the other hand, unsupervised deep…
Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either monocular depth…
Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…
The ground-to-satellite image matching/retrieval was initially proposed for city-scale ground camera localization. This work addresses the problem of improving camera pose accuracy by ground-to-satellite image matching after a coarse…
Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding…
Cross-view video geo-localization (CVGL) aims to derive GPS trajectories from street-view videos by aligning them with aerial-view images. Despite their promising performance, current CVGL methods face significant challenges. These methods…