5 papers
DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion
Sithu Aung, Viktor Kocur, Yaqing Ding +2
Global Structure-from-Motion (SfM) is an efficient paradigm for recovering camera poses and sparse 3D structure from unordered images. However, its reliance on scale-ambiguous epip…
Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth
Viktor Kocur, Sithu Aung, Gabrielle Flood +4
Monocular depth estimation has improved significantly in recent years, driven by increasingly powerful models and large-scale training data. Predicted depth is increasingly used as…
Decoupled Geometric Parameterization and its Application in Deep Homography Estimation
Yao Huang, Si-Yuan Cao, Yaqing Ding +8
Planar homography, with eight degrees of freedom (DOFs), is fundamental in numerous computer vision tasks. While the positional offsets of four corners are widely adopted (especial…
Are Minimal Radial Distortion Solvers Really Necessary for Relative Pose Estimation?
Viktor Kocur, Charalambos Tzamos, Yaqing Ding +3
Estimating the relative pose between two cameras is a fundamental step in many applications such as Structure-from-Motion. The common approach to relative pose estimation is to app…
A Guide to Structureless Visual Localization
Vojtech Panek, Qunjie Zhou, Yaqing Ding +4
Visual localization algorithms, i.e., methods that estimate the camera pose of a query image in a known scene, are core components of many applications, including self-driving cars…