Related papers: ACE-G: Improving Generalization of Scene Coordinat…

Scene coordinates regression (SCR), i.e., predicting 3D coordinates for every pixel of a given image, has recently shown promising potential. However, existing methods remain limited to small scenes memorized during training, and thus…

Scene coordinate regression (SCR) methods are a family of visual localization methods that directly regress 2D-3D matches for camera pose estimation. They are effective in small-scale scenes but face significant challenges in large-scale…

Learning-based visual localization methods that use scene coordinate regression (SCR) offer the advantage of smaller map sizes. However, on datasets with complex illumination changes or image-level ambiguities, it remains a less robust…

Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…

Visual localization is considered to be one of the crucial parts in many robotic and vision systems. While state-of-the art methods that relies on feature matching have proven to be accurate for visual localization, its requirements for…

Scene coordinate regression (SCR) methods have emerged as a promising area of research due to their potential for accurate visual localization. However, many existing SCR approaches train on samples from all image regions, including dynamic…

Autonomous flight in GPS-denied indoor spaces requires trajectories that keep visual-localization error tightly bounded across varied missions. Map-based visual localization methods such as feature matching require computationally intensive…

Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in…

We address the task of estimating camera parameters from a set of images depicting a scene. Popular feature-based structure-from-motion (SfM) tools solve this task by incremental reconstruction: they repeat triangulation of sparse 3D points…

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…

Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few training samples as possible. The existing state-of-the-art…

Camera relocalization involving a prior 3D reconstruction plays a crucial role in many mixed reality and robotics applications. Estimating the camera pose directly with respect to pre-built 3D models can be prohibitively expensive for…

Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training…

Image-based camera relocalization is an important problem in computer vision and robotics. Recent works utilize convolutional neural networks (CNNs) to regress for pixels in a query image their corresponding 3D world coordinates in the…

We present a novel neural RGB-D Simultaneous Localization And Mapping (SLAM) system that learns an implicit map of the scene in real time. For the first time, we explore the use of Scene Coordinate Regression (SCR) as the core implicit map…

Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding…

We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low…

Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain…

Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their…

Efficient localization and high-quality rendering in large-scale scenes remain a significant challenge due to the computational cost involved. While Scene Coordinate Regression (SCR) methods perform well in small-scale localization, they…