Related papers: Depth Ranging Performance Evaluation and Improveme…

Multi-sensor fusion has significant potential in perception tasks for both indoor and outdoor environments. Especially under challenging conditions such as adverse weather and low-light environments, the combined use of millimeter-wave…

Image segmentation is a vital task for providing human assistance and enhancing autonomy in our daily lives. In particular, RGB-D segmentation-leveraging both visual and depth cues-has attracted increasing attention as it promises richer…

RGB-D salient object detection (SOD) recently has attracted increasing research interest by benefiting conventional RGB SOD with extra depth information. However, existing RGB-D SOD models often fail to perform well in terms of both…

Active depth cameras suffer from several limitations, which cause incomplete and noisy depth maps, and may consequently affect the performance of RGB-D Odometry. To address this issue, this paper presents a visual odometry method based on…

Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution. Accurate depth sensors such as LiDARs are often heavy, expensive and can only…

Accurate building segmentation from high-resolution RGB imagery remains challenging due to spectral similarity with non-building features, shadows, and irregular building geometries. In this study, we present a comprehensive deep learning…

We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning-based instance segmentation and…

Fine-detailed reconstructions are in high demand in many applications. However, most of the existing RGB-D reconstruction methods rely on pre-calculated accurate camera poses to recover the detailed surface geometry, where the…

Single image depth estimation (SIDE) plays a crucial role in 3D computer vision. In this paper, we propose a two-stage robust SIDE framework that can perform blind SIDE for both indoor and outdoor scenes. At the first stage, the scene…

Benefiting from the spatial cues embedded in depth images, recent progress on RGB-D saliency detection shows impressive ability on some challenge scenarios. However, there are still two limitations. One hand is that the pooling and…

Robust 6DoF pose estimation with mobile devices is the foundation for applications in robotics, augmented reality, and digital twin localization. In this paper, we extensively investigate the robustness of existing RGBD-based 6DoF pose…

Using the raw data from consumer-level RGB-D cameras as input, we propose a deep-learning based approach to efficiently generate RGB-D images with completed information in high resolution. To process the input images in low resolution with…

Depth sensing cameras (e.g., Kinect sensor, Tango phone) can acquire color and depth images that are registered to a common viewpoint. This opens the possibility of developing algorithms that exploit the advantages of both sensing…

Depth sensing is a critical function for robotic tasks such as localization, mapping and obstacle detection. There has been a significant and growing interest in depth estimation from a single RGB image, due to the relatively low cost and…

Relative pose estimation for RGBD cameras is crucial in a number of applications. Previous approaches either rely on the RGB aspect of the images to estimate pose thus not fully making use of depth in the estimation process or estimate pose…

Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have…

Human action recognition still exists many challenging problems such as different viewpoints, occlusion, lighting conditions, human body size and the speed of action execution, although it has been widely used in different areas. To tackle…

In this paper, we extend the recently developed continuous visual odometry framework for RGB-D cameras to an adaptive framework via online hyperparameter learning. We focus on the case of isotropic kernels with a scalar as the length-scale.…

Sparse depth measurements are widely available in many applications such as augmented reality, visual inertial odometry and robots equipped with low cost depth sensors. Although such sparse depth samples work well for certain applications…

Deep learning approaches have achieved highly accurate face recognition by training the models with very large face image datasets. Unlike the availability of large 2D face image datasets, there is a lack of large 3D face datasets available…