Related papers: Moving SLAM: Fully Unsupervised Deep Learning in N…
In object-based Simultaneous Localization and Mapping (SLAM), 6D object poses offer a compact representation of landmark geometry useful for downstream planning and manipulation tasks. However, measurement ambiguity then arises as objects…
While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult…
The 3D-zoom operation is the positive translation of the camera in the Z-axis, perpendicular to the image plane. In contrast, the optical zoom changes the focal length and the digital zoom is used to enlarge a certain region of an image to…
Moving objects can greatly jeopardize the performance of a visual simultaneous localization and mapping (vSLAM) system which relies on the static-world assumption. Motion removal have seen successful on solving this problem. Two main…
We present an unsupervised simultaneous learning framework for the task of monocular camera re-localization and depth estimation from unlabeled video sequences. Monocular camera re-localization refers to the task of estimating the absolute…
The traditional Simultaneous Localization And Mapping (SLAM) systems rely on the assumption of a static environment and fail to accurately estimate the system's location when dynamic objects are present in the background. While…
In this paper, we present a tightly-coupled visual-inertial object-level multi-instance dynamic SLAM system. Even in extremely dynamic scenes, it can robustly optimise for the camera pose, velocity, IMU biases and build a dense 3D…
As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days. However, non-geometric modules of traditional SLAM algorithms are limited by data…
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…
Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit…
We propose Unblur-SLAM, a novel RGB SLAM pipeline for sharp 3D reconstruction from blurred image inputs. In contrast to previous work, our approach is able to handle different types of blur and demonstrates state-of-the-art performance in…
We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our knowledge, our system is among the first to utilize the camera…
Simultaneous Localization and Mapping (SLAM) has become a critical technology for intelligent transportation systems and autonomous robots and is widely used in autonomous driving. However, traditional manual feature-based methods in…
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…
We present a novel approach for unsupervised learning of depth and ego-motion from monocular video. Unsupervised learning removes the need for separate supervisory signals (depth or ego-motion ground truth, or multi-view video). Prior work…
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…
Recent progress in object pose prediction provides a promising path for robots to build object-level scene representations during navigation. However, as we deploy a robot in novel environments, the out-of-distribution data can degrade the…
We propose the first 4D tracking and mapping method that jointly performs camera localization and non-rigid surface reconstruction via differentiable rendering. Our approach captures 4D scenes from an online stream of color images with…
The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption limits the use of most visual SLAM systems in populated real-world environments, which are the target of several relevant applications like service…
In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…