Related papers: EPI-based Oriented Relation Networks for Light Fie…
The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small…
Depth estimation from a single image is a fundamental problem in computer vision. In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for depth prediction.…
Incorporating boundaries of the imaging object as a priori information to imaging algorithms can significantly improve the performance of electromagnetic medical imaging systems. To avoid overly complicating the system by using different…
Ground Terrain Recognition is a difficult task as the context information varies significantly over the regions of a ground terrain image. In this paper, we propose a novel approach towards ground-terrain recognition via modeling the…
Many tasks performed by autonomous vehicles such as road marking detection, object tracking, and path planning are simpler in bird's-eye view. Hence, Inverse Perspective Mapping (IPM) is often applied to remove the perspective effect from a…
Light-field microscopes are able to capture spatial and angular information of incident light rays. This allows reconstructing 3D locations of neurons from a single snap-shot.In this work, we propose a model-inspired deep learning approach…
This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods…
Detecting oriented objects along with estimating their rotation information is one crucial step for analyzing remote sensing images. Despite that many methods proposed recently have achieved remarkable performance, most of them directly…
In this study, we propose a high-performance disparity (depth) estimation method using dual-pixel (DP) images with few parameters. Conventional end-to-end deep-learning methods have many parameters but do not fully exploit disparity…
Super-resolution of LiDAR range images is crucial to improving many downstream tasks such as object detection, recognition, and tracking. While deep learning has made a remarkable advances in super-resolution techniques, typical…
Enhancing visual odometry by exploiting sparse depth measurements from LiDAR is a promising solution for improving tracking accuracy of an odometry. Most existing works utilize a monocular pinhole camera, yet could suffer from poor…
Self-supervised depth estimators have recently shown results comparable to the supervised methods on the challenging single image depth estimation (SIDE) task, by exploiting the geometrical relations between target and reference views in…
Flexible intelligent metasurface (FIM) has recently received considerable interest due to its advantage in realizing a better channel condition by dynamically morphing its surface shape. An FIM consists of multiple elements deposited on a…
Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth…
The past decade has witnessed significant progress on detecting objects in aerial images that are often distributed with large scale variations and arbitrary orientations. However most of existing methods rely on heuristically defined…
Aberration-corrected scanning transmission electron microscopes (STEM) provide sub-angstrom lateral resolution; however, the large convergence angle greatly reduces the depth of field. For microscopes with a small depth of field,…
Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation…
Estimating relative pose from image pairs fundamentally requires only a minimal subset of geometrically consistent correspondences. However, most learning-based approaches rely on dense matching or direct regression, leading to redundancy…
Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems,…
Convolutional neural networks (CNNs) have attracted increasing attention in the remote sensing community. Most CNNs only take the last fully-connected layers as features for the classification of remotely sensed images, discarding the other…