Generative models can produce impressively realistic images. This paper demonstrates that
generated images have geometric features different from those of real images. We build a …

In contrast to sparse keypoints, a handful of line segments can concisely encode the high-
level scene layout, as they often delineate the main structural elements. In addition to …

Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are
detected in each view of a scene. Crucially, the detected points need to be consistent …

An image line segment is a fundamental low-level visual feature that delineates straight,
slender, and uninterrupted portions of objects and scenarios within images. Detection and …

This paper proposes an illumination-robust visual odometry (VO) system that incorporates
both accelerated learning-based corner point algorithms and an extended line feature …

In this paper, we present an efficient visual SLAM system designed to tackle both short-term
and long-term illumination challenges. Our system adopts a hybrid approach that combines …

We propose an approach for estimating the relative pose between calibrated image pairs by
jointly exploiting points, lines, and their coincidences in a hybrid manner. We investigate all …

From a single image, visual cues can help deduce intrinsic and extrinsic camera parameters
like the focal length and the gravity direction. This single-image calibration can benefit …

Real-world objects and environments are predominantly composed of edge features
including straight lines and curves. Such edges are crucial elements for various applications …

We introduce a lightweight and accurate localization method that only utilizes the geometry
of 2D-3D lines. Given a pre-captured 3D map our approach localizes a panorama image …