11 accepted papers
Bundle adjustment is a long-standing problem in computer vision that solves for camera parameters and 3D point coordinates from 2D image observations. While there has been much work on various aspects, like adaptation to different camera models and sensors, and considerations for solving the optimiz
Outliers are ubiquitous in geometric vision contexts such as pose estimation and mapping, leading to inaccurate estimates. While robust loss functions can tackle outliers, it is challenging to make the estimation robust to the choice of initialization and to estimate the appropriate robust loss shap…
"Graduated Non-Convexity (GNC) is a robust estimation method in which an objective function is progressively annealed starting from a smooth convex form to one that represents the desired objective function. Such annealing is achieved by modifying a scale parameter in the objective function that is…
In Structure-from-Motion (SfM) the underlying viewgraphs of unordered image collections generally have a highly redundant set of edges that can be sparsified for efficiency without significant loss of reconstruction quality. Often there are also false edges due to incorrect image retrieval and repea…
Geometric estimation problems in vision are often solved via minimization of statistical loss functions which account for the presence of outliers in the observations. The corresponding energy landscape often has many local minima. Many approaches attempt to avoid local minima by annealing the scale…
In 3D computer vision, translation averaging solves for absolute translations given a set of pairwise relative translation directions. While there has been much work on robustness to outliers and studies on the uniqueness of the solution, this paper deals with a distinctly different problem of sensi…
"Translation averaging methods use the consistency of input translation directions to solve for camera translations. However, translation directions obtained using epipolar geometry are error-prone. This paper argues that the improved accuracy of translation averaging should be leveraged to mitigate…
We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the…
We present a robust, fast and accurate method for registration of 3D scans. Using correspondences, our method optimizes a robust cost function on the intrinsic representation of rigid motions, i.e., the Special Euclidean group SE(3). We exploit the geometric properties of Lie groups as well as the r…
In recent years, there have been a variety of proposals for high quality 3D reconstruction by fusion of depth and normal maps that contain good low and high frequency information respectively. Typically, these methods create an initial mesh representation of the complete object or scene being scanne…
In this paper, we propose a novel uncalibrated photometric method for refining depth maps of multi-albedo objects obtained from consumer depth cameras like Kinect. Existing uncalibrated photometric methods either assume that the object has constant albedo or rely on segmenting images into constant a…