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 …

Can we relocalize in a scene represented by a single reference image? Standard visual
relocalization requires hundreds of images and scale calibration to build a scene-specific …

Learning-based visual relocalizers exhibit leading pose accuracy, but require hours or days
of training. Since training needs to happen on each new scene again, long training times …

With the rise of deep learning, there is a fundamental change in visual simultaneous
localization and map** (SLAM) algorithms toward develo** different modules trained as …

In this work, we seek to predict camera poses across scenes with a multi-task learning
manner, where we view the localization of each scene as a new task. We propose OFVL …

Absolute pose regressor (APR) networks are trained to estimate the pose of the camera
given a captured image. They compute latent image representations from which the camera …

Absolute camera pose regressors estimate the position and orientation of a camera given
the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron …

Deducing the 3D structure of endoscopic scenes from images is exceedingly challenging. In
addition to deformation and view-dependent lighting, tubular structures like the colon …

Visual localization, a vital component of many visual applications, has been tackled by
scene coordinates regression (SCoRe) methods that leverage neural networks to predict …

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 …