Related papers: Fast, Robust, Continuous Monocular Egomotion Compu…

In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input representation of the events in the form of a discretized…

In this paper, two simple principal component regression methods for estimating the optical flow between frames of video sequences according to a pel-recursive manner are introduced. These are easy alternatives to dealing with mixtures of…

Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant attention. Grounded in subjective logic, EDL derives Dirichlet…

With recent advances in embodied agents and AR devices, egocentric observations are readily available as input for real-world interactive online applications. However, egocentric viewpoints can only sporadically observe hands, in addition…

In many robotics and VR/AR applications, fast camera motions lead to a high level of motion blur, causing existing camera pose estimation methods to fail. In this work, we propose a novel framework that leverages motion blur as a rich cue…

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer…

Monocular cameras are extensively employed in indoor robotics, but their performance is limited in visual odometry, depth estimation, and related applications due to the absence of scale information.Depth estimation refers to the process of…

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix,…

A key component of Visual Simultaneous Localization and Mapping (VSLAM) is estimating relative camera poses using matched keypoints. Accurate estimation is challenged by noisy correspondences. Classical methods rely on stochastic hypothesis…

We propose MoRe-ERL, a framework that combines Episodic Reinforcement Learning (ERL) and residual learning, which refines preplanned reference trajectories into safe, feasible, and efficient task-specific trajectories. This framework is…

Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability…

To validate a clinically accessible approach for quantifying the Upper Extremity Reachable Workspace (UERW) using a single (monocular) camera and Artificial Intelligence (AI)-driven Markerless Motion Capture (MMC) for biomechanical…

We present EgoCOL, an egocentric camera pose estimation method for open-world 3D object localization. Our method leverages sparse camera pose reconstructions in a two-fold manner, video and scan independently, to estimate the camera pose of…

This letter proposes a reactive navigation strategy for recovering the altitude, translational velocity and orientation of Micro Aerial Vehicles. The main contribution lies in the direct and tight fusion of Inertial Measurement Unit (IMU)…

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative…

The Extreme Learning Machine (ELM) is a growing statistical technique widely applied to regression problems. In essence, ELMs are single-layer neural networks where the hidden layer weights are randomly sampled from a specific distribution,…

We present a generative method to estimate 3D human motion and body shape from monocular video. Under the assumption that starting from an initial pose optical flow constrains subsequent human motion, we exploit flow to find temporally…

We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single trajectory, i.e., without resets. We propose Nonepisodic…

While on-body device-based human motion estimation is crucial for applications such as XR interaction, existing methods often suffer from poor wearability, expensive hardware, and cumbersome calibration, which hinder their adoption in daily…

We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…