Related papers: Consistent Direct Time-of-Flight Video Depth Super…
Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments. For example, transparent materials frequently elude detection by depth sensors;…
As one of the automotive sensors that have emerged in recent years, 4D millimeter-wave radar has a higher resolution than conventional 3D radar and provides precise elevation measurements. But its point clouds are still sparse and noisy,…
Drone-camera based human activity recognition (HAR) has received significant attention from the computer vision research community in the past few years. A robust and efficient HAR system has a pivotal role in fields like video…
Depth completion in dynamic scenes poses significant challenges due to rapid ego-motion and object motion, which can severely degrade the quality of input modalities such as RGB images and LiDAR measurements. Conventional RGB-D sensors…
Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and…
An indirect Pulse-based Time-of-Flight camera can be modelled as a linear sensing system in which the target's depth is recovered from few measurements through a sensing matrix formed by a set of demodulation functions. Each demodulation…
Superconducting nanowire single photon detectors (SNSPDs) emerged in the last decade as a disruptive technology that features performance characteristics, such as high sensitivity, dynamic range and temporal accuracy, which are ideally…
Low-cost mobile rovers often operate on uneven terrain where small bumps or tilts are difficult to perceive visually but can significantly affect locomotion stability. To address this problem, we explore a smartphone-based structured-light…
To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps fusion. Recent studies concentrate on deep neural…
Depth estimation is crucial for intelligent systems, enabling applications from autonomous navigation to augmented reality. While traditional stereo and active depth sensors have limitations in cost, power, and robustness, dual-pixel (DP)…
The detection of small objects in aerial images is a fundamental task in the field of computer vision. Moving objects in aerial photography have problems such as different shapes and sizes, dense overlap, occlusion by the background, and…
Event cameras sense the intensity changes asynchronously and produce event streams with high dynamic range and low latency. This has inspired research endeavors utilizing events to guide the challenging video superresolution (VSR) task. In…
The advancement of autonomous drones, essential for sectors such as remote sensing and emergency services, is hindered by the absence of training datasets that fully capture the environmental challenges present in real-world scenarios,…
Imaging through a strongly diffusive medium remains an outstanding challenge in particular in association with applications in biological and medical imaging. Here we propose a method based on a single-photon time-of-flight camera that…
We present a real-time approach for image-based localization within large scenes that have been reconstructed offline using structure from motion (Sfm). From monocular video, our method continuously computes a precise 6-DOF camera pose, by…
We introduce InFusionSurf, an innovative enhancement for neural radiance field (NeRF) frameworks in 3D surface reconstruction using RGB-D video frames. Building upon previous methods that have employed feature encoding to improve…
Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…
Visual-LiDAR odometry is a critical component for autonomous system localization, yet achieving high accuracy and strong robustness remains a challenge. Traditional approaches commonly struggle with sensor misalignment, fail to fully…
Low-light image super-resolution (LLISR) is essential for restoring fine visual details and perceptual quality under insufficient illumination conditions with ubiquitous low-resolution devices. Although pioneer methods achieve high…
Depth-from-Focus (DFF) enables precise depth estimation by analyzing focus cues across a stack of images captured at varying focal lengths. While recent learning-based approaches have advanced this field, they often struggle in complex…