Related papers: Large-scale DSM registration via motion averaging
Cortical surface registration is a fundamental tool for neuroimaging analysis that has been shown to improve the alignment of functional regions relative to volumetric approaches. Classically, image registration is performed by optimizing a…
As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years. It is efficient and accurate for sparse scenes, but suffers an inevitable trade-off between…
Deformable registration consists of finding the best dense correspondence between two different images. Many algorithms have been published, but the clinical application was made difficult by the high calculation time needed to solve the…
In crowded scenes, detection and localization of abnormal behaviors is challenging in that high-density people make object segmentation and tracking extremely difficult. We associate the optical flows of multiple frames to capture…
Online augmentation of an oblique aerial image sequence with structural information is an essential aspect in the process of 3D scene interpretation and analysis. One key aspect in this is the efficient dense image matching and depth…
The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications. Using a multispectral camera setup can improve this process by…
Deformable image registration is a very important field of research in medical imaging. Recently multiple deep learning approaches were published in this area showing promising results. However, drawbacks of deep learning methods are the…
In this paper, we propose a novel approach to address the problem of camera and radar sensor fusion for 3D object detection in autonomous vehicle perception systems. Our approach builds on recent advances in deep learning and leverages the…
Many algorithms for surface registration risk producing significant errors if surfaces are significantly nonisometric. Manifold learning has been shown to be effective at improving registration quality, using information from an entire…
LiDAR odometry is a fundamental task for various areas such as robotics, autonomous driving. This problem is difficult since it requires the systems to be highly robust running in noisy real-world data. Existing methods are mostly local…
Deep metrics have been shown effective as similarity measures in multi-modal image registration; however, the metrics are currently constructed from aligned image pairs in the training data. In this paper, we propose a strategy for learning…
Given dense image feature correspondences of a non-rigidly moving object across multiple frames, this paper proposes an algorithm to estimate its 3D shape for each frame. To solve this problem accurately, the recent state-of-the-art…
Image registration plays an important role in medical image analysis. Conventional optimization based methods provide an accurate estimation due to the iterative process at the cost of expensive computation. Deep learning methods such as…
In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only. Our contribution to this unexplored task is a novel formulation of motion segmentation as a…
We present a novel approach for relocalization or place recognition, a fundamental problem to be solved in many robotics, automation, and AR applications. Rather than relying on often unstable appearance information, we consider a situation…
Given a collection of points $S \subset \mathbb{R}^N$, which is partitioned into $M$ overlapping subsets $\{S_i\}_{i=1}^M$, and approximate data $\{D_i\}_{i=1}^M$ associated with the subsets, one may seek a consistent merged dataset $D$…
We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches…
This paper contributes a novel realtime multi-person motion capture algorithm using multiview video inputs. Due to the heavy occlusions in each view, joint optimization on the multiview images and multiple temporal frames is indispensable,…
Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling…
Computer vision techniques have been used to produce accurate and generic crowd count estimators in recent years. Due to severe occlusions, appearance variations, perspective distortions and illumination conditions, crowd counting is a very…