Related papers: SO(3)-invariant asymptotic observers for dense dep…

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

This work proposes a novel deep network architecture to solve the camera Ego-Motion estimation problem. A motion estimation network generally learns features similar to Optical Flow (OF) fields starting from sequences of images. This OF can…

We describe a non-parametric, "example-based" method for estimating the depth of an object, viewed in a single photo. Our method consults a database of example 3D geometries, searching for those which look similar to the object in the…

This paper introduces a novel approach for image and video orientation estimation by leveraging depth distribution in natural images. The proposed method estimates the orientation based on the depth distribution across different quadrants…

Video depth estimation is crucial in various applications, such as scene reconstruction and augmented reality. In contrast to the naive method of estimating depths from images, a more sophisticated approach uses temporal information,…

Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object motion can equally be…

This paper explores visual motion-based invariants, resulting in a new instantaneous domain where: a) the stationary environment is perceived as unchanged, even as the 2D images undergo continuous changes due to camera motion, b) obstacles…

We introduce OpenVO, a novel framework for Open-world Visual Odometry (VO) with temporal awareness under limited input conditions. OpenVO effectively estimates real-world-scale ego-motion from monocular dashcam footage with varying…

This paper presents a deterministic hybrid observer for the attitude dynamics of a rigid body that guarantees global asymptotical stability. Any smooth attitude observer suffers from the inherent topological restriction that it is…

We propose a method to compute depth maps for every sub-aperture image in a light field in a view consistent way. Previous light field depth estimation methods typically estimate a depth map only for the central sub-aperture view, and…

Recovering the 3D structure of the surrounding environment is an essential task in any vision-controlled Structure-from-Motion (SfM) scheme. This paper focuses on the theoretical properties of the SfM, known as the incremental active depth…

Monocular depth estimation is a critical task for autonomous driving and many other computer vision applications. While significant progress has been made in this field, the effects of viewpoint shifts on depth estimation models remain…

This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the quality of deep neural network predictions. In a supervised learning scenario, the quality of predictions is intrinsically related to the…

Current deep visual local feature detectors do not model the spatial uncertainty of detected features, producing suboptimal results in downstream applications. In this work, we propose two post-hoc covariance estimates that can be plugged…

This paper considers the problem of nonlinear attitude estimation for a rigid body system using intermittent and multi-rate inertial vector measurements as well as continuous (high-rate) angular velocity measurements. Two types of hybrid…

This paper proposes a concise, elegant, and robust pipeline to estimate smooth camera trajectories and obtain dense point clouds for casual videos in the wild. Traditional frameworks, such as ParticleSfM~\cite{zhao2022particlesfm}, address…

Traditional Visual Odometry (VO) and Visual Inertial Odometry (VIO) methods rely on a 'pose-centric' paradigm, which computes absolute camera poses from the local map thus requires large-scale landmark maintenance and continuous map…

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…

3D reconstruction of depth and motion from monocular video in dynamic environments is a highly ill-posed problem due to scale ambiguities when projecting to the 2D image domain. In this work, we investigate the performance of the current…

In this paper, we consider the problem of designing an asymptotic observer for a nonlin-ear dynamical system in discrete-time following Luenberger's original idea. This approach is a two-step design procedure. In a first step, the problem…