Related papers: Relative Pose Regression with Pose Auto-Encoders: …

Image-based localization, or camera relocalization, is a fundamental problem in computer vision and robotics, and it refers to estimating camera pose from an image. Recent state-of-the-art approaches use learning based methods, such as…

Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for…

Active camera relocalization (ACR) is a new problem in computer vision that significantly reduces the false alarm caused by image distortions due to camera pose misalignment in fine-grained change detection (FGCD). Despite the fruitful…

Monocular 3D human pose estimation (HPE) methods estimate the 3D positions of joints from individual images. Existing 3D HPE approaches often use the cropped image alone as input for their models. However, the relative depths of joints…

In this work, we propose HyperPose, which utilizes hyper-networks in absolute camera pose regressors. The inherent appearance variations in natural scenes, attributable to environmental conditions, perspective, and lighting, induce a…

Visual Place Recognition (VPR) is a fundamental task that allows a robotic platform to successfully localise itself in the environment. For decentralised VPR applications where the visual data has to be transmitted between several agents,…

Relative position encoding (RPE) is important for transformer to capture sequence ordering of input tokens. General efficacy has been proven in natural language processing. However, in computer vision, its efficacy is not well studied and…

Camera pose estimation is an important problem in computer vision. Common techniques either match the current image against keyframes with known poses, directly regress the pose, or establish correspondences between keypoints in the image…

Autonomous driving systems rely on accurate perception and localization of the ego car to ensure safety and reliability in challenging real-world driving scenarios. Public datasets play a vital role in benchmarking and guiding advancement…

We propose a new method for estimating the relative pose between two images, where we jointly learn keypoint detection, description extraction, matching and robust pose estimation. While our architecture follows the traditional pipeline for…

Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples…

Recovering camera poses from a set of images is a foundational task in 3D computer vision, which powers key applications such as 3D scene/object reconstructions. Classic methods often depend on feature correspondence, such as keypoints,…

Two-view pose estimation is essential for map-free visual relocalization and object pose tracking tasks. However, traditional matching methods suffer from time-consuming robust estimators, while deep learning-based pose regressors only…

Visual relocalization aims to estimate the pose of a camera from one or more images. In recent years deep learning based pose regression methods have attracted many attentions. They feature predicting the absolute poses without relying on…

Neural Radiance Fields (NeRF) have recently demonstrated photo-realistic results for the task of novel view synthesis. In this paper, we propose to apply novel view synthesis to the robot relocalization problem: we demonstrate improvement…

We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localization accuracy of state-of-the-art absolute pose regression…

In this paper, we propose a new image-based visual place recognition (VPR) framework by exploiting the structural cues in bird's-eye view (BEV) from a single monocular camera. The motivation arises from two key observations about place…

Multi-scene absolute pose regression addresses the demand for fast and memory-efficient camera pose estimation across various real-world environments. Nowadays, transformer-based model has been devised to regress the camera pose directly in…

Accurate camera pose estimation is a fundamental requirement for numerous applications, such as autonomous driving, mobile robotics, and augmented reality. In this work, we address the problem of estimating the global 6 DoF camera pose from…

The performance of human pose estimation depends on the spatial accuracy of keypoint localization. Most existing methods pursue the spatial accuracy through learning the high-resolution (HR) representation from input images. By the…