Related papers: RGB-Only Supervised Camera Parameter Optimization …
Markerless human motion capture (mocap) from multiple RGB cameras is a widely studied problem. Existing methods either need calibrated cameras or calibrate them relative to a static camera, which acts as the reference frame for the mocap…
Visual odometry is the process of estimating the position and orientation of a camera by analyzing the images associated to it. This paper develops a quick and accurate approach to visual odometry of a moving RGB-D camera navigating on a…
3D Gaussian Splatting (3DGS) has become a popular solution in SLAM, as it can produce high-fidelity novel views. However, previous GS-based methods primarily target indoor scenes and rely on RGB-D sensors or pre-trained depth estimation…
In this paper, we introduce a novel formulation for camera motion estimation that integrates RGB-D images and inertial data through scene flow. Our goal is to accurately estimate the camera motion in a rigid 3D environment, along with the…
Most monocular and physics-based human pose tracking methods, while achieving state-of-the-art results, suffer from artifacts when the scene does not have a strictly flat ground plane or when the camera is moving. Moreover, these methods…
Mapping and localization are essential capabilities of robotic systems. Although the majority of mapping systems focus on static environments, the deployment in real-world situations requires them to handle dynamic objects. In this paper,…
In this paper, a simultaneous localization and mapping (SLAM) method that eliminates the influence of moving objects in dynamic environments is proposed. This method utilizes the correlation between map points to separate points that are…
Real-time dense scene reconstruction during unstable camera motions is crucial for robotics, yet current RGB-D SLAM systems fail when cameras experience large viewpoint changes, fast motions, or sudden shaking. Classical optimization-based…
{Recognizing human interactions is essential for social robots as it enables them to navigate safely and naturally in shared environments. Conventional robotic systems however often focus on obstacle avoidance, neglecting social cues…
We present a physics-driven framework for accurate evaluation of discrete spectral bands using a low-cost multispectral setup built from off-the-shelf RGB cameras and narrow multi-band optical filters. The approach starts by explicitly…
Commonly available prior information, such as BIM models, floor plans, and remote sensing images, can provide valuable geometric and semantic context for autonomous robotic systems. In this paper, we treat observations from fixed external…
We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video. While camera rotation estimation is a well-studied problem, no previous methods exhibit both high accuracy and acceptable…
Video object segmentation is a fundamental step in many advanced vision applications. Most existing algorithms are based on handcrafted features such as HOG, super-pixel segmentation or texture-based techniques, while recently deep features…
We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in…
The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will…
Feature matching is a fundamental and crucial process in visual SLAM, and precision has always been a challenging issue in feature matching. In this paper, based on a multi-level fine matching strategy, we propose a new feature matching…
Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many methods directly filter out dynamic objects, resulting in…
3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM)…
Holistic 3D indoor scene understanding refers to jointly recovering the i) object bounding boxes, ii) room layout, and iii) camera pose, all in 3D. The existing methods either are ineffective or only tackle the problem partially. In this…
Aligning partial views of a scene into a single whole is essential to understanding one's environment and is a key component of numerous robotics tasks such as SLAM and SfM. Recent approaches have proposed end-to-end systems that can…