Due to the lack of camera parameter information for in-the-wild images, existing 3D human
pose and shape (HPS) estimation methods make several simplifying assumptions: weak …

Abstract We present Neural-Guided RANSAC (NG-RANSAC), an extension to the classic
RANSAC algorithm from robust optimization. NG-RANSAC uses prior information to improve …

Ordinal regression attempts to solve classification problems in which categories are not
independent, but rather follow a natural order. It is crucial to classify each class correctly …

Geometric camera calibration is often required for applications that understand the
perspective of the image. We propose perspective fields as a representation that models the …

Calibration of wide field-of-view cameras is a fundamental step for numerous visual media
production applications, such as 3D reconstruction, image undistortion, augmented reality …

Classical work on line segment detection is knowledge-based; it uses carefully designed
geometric priors using either image gradients, pixel grou**s, or Hough transform variants …

We propose the first general framework to automatically correct different types of geometric
distortion in a single input image. Our proposed method employs convolutional neural …

Most current single image camera calibration methods rely on specific image features or
user input, and cannot be applied to natural images captured in uncontrolled settings. We …

Single image calibration is the problem of predicting the camera parameters from one
image. This problem is of importance when dealing with images collected in uncontrolled …

A number of computer vision deep regression approaches report improved results when
adding a classification loss to the regression loss. Here, we explore why this is useful in …