DSR: Direct Self-Rectification for Uncalibrated Dual-Lens Cameras

Abstract

With the developments of dual-lens camera modules, depth information representing the third dimension of the captured scenes becomes available for smartphones. It is estimated by stereo matching algorithms, taking as input the two views captured by dual-lens cameras at slightly different viewpoints. Depth-of-field rendering (also be referred to as synthetic defocus or bokeh) is one of the trending depthbased applications. However, to achieve fast depth estimation on smartphones, the stereo pairs need to be rectified in the first place. In this paper, we propose a cost-effective solution to perform stereo rectification for dual-lens cameras called direct self-rectification, short for DSR 1 . It removes the need of individual offline calibration for every pair of dual-lens cameras. In addition, the proposed solution is robust to the slight movements, e.g., due to collisions, of the dual-lens cameras after fabrication. Different with existing self-rectification approaches, our approach computes the homography in a novel way with zero geometric distortions introduced to the master image. It is achieved by directly minimizing the vertical displacements of corresponding points between the original master image and the transformed slave image. Our method is evaluated on both realistic and synthetic stereo image pairs, and produces superior results compared to the calibrated rectification or other self-rectification approaches.

Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module

“…In fact, modern RGB cameras are often equipped with optical image stabilization (OIS) systems which dynamically changes the principal points, alongside with other mild calibration degradation to the ToF RGB-D camera module. These impacts can be sufficiently modeled by the changes of the principal point c x , c y of the RGB camera, and the relative translation parameters t x , t y [7,40]; while the rest of the parameters can be viewed as unchanged. Hence, it brings the need of performing online calibration and alignment for ToF RGB-D camera modules.…”

Accurate Uncalibrated Rectification Using Feature Matching Re-Selection

“…Using the same Quasi-Euclidean constraints, Hyunsuk Ko et al [22] enhanced the algorithm by taking into account the impact of multiple types of geometric distortions in their computations. In the case of handheld devices such as smartphones, Ruichao Xiao et al [23] proposed an low distortion rectification method under uncalibrated scenarios.…”