English
Related papers

Related papers: Driven to Distraction: Self-Supervised Distractor …

200 papers

In this research we present a novel algorithm for background subtraction using a moving camera. Our algorithm is based purely on visual information obtained from a camera mounted on an electric bus, operating in downtown Reno which…

Robotics · Computer Science 2018-11-19 Sotirios Diamantas , Kostas Alexis

Hybrid pipelines that combine deep learning with classical optimization have established themselves as the dominant approach to visual odometry (VO). By integrating neural network predictions with bundle adjustment, these models estimate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Vlardimir Yugay , Duy-Kien Nguyen , Theo Gevers , Cees G. M. Snoek , Martin R. Oswald

The stability of visual odometry (VO) systems is undermined by degraded image quality, especially in environments with significant illumination changes. This study employs a deep reinforcement learning (DRL) framework to train agents for…

Robotics · Computer Science 2024-12-24 Shuyang Zhang , Jinhao He , Yilong Zhu , Jin Wu , Jie Yuan

Rolling Shutter (RS) cameras have become popularized because of low-cost imaging capability. However, the RS cameras suffer from undesirable artifacts when the camera or the subject is moving, or illumination condition changes. For that…

Computer Vision and Pattern Recognition · Computer Science 2017-04-25 Chang-Ryeol Lee , Kuk-Jin Yoon

In this paper, an approach for reducing the drift in monocular visual odometry algorithms is proposed based on a feedforward neural network. A visual odometry algorithm computes the incremental motion of the vehicle between the successive…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Hassan Wagih , Mostafa Osman , Mohamed I. Awad , Sherif Hammad

Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with…

Computer Vision and Pattern Recognition · Computer Science 2020-05-14 Shunkai Li , Xin Wang , Yingdian Cao , Fei Xue , Zike Yan , Hongbin Zha

Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dynamic nature of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Xiuzhe Wu , Xiaoyang Lyu , Qihao Huang , Yong Liu , Yang Wu , Ying Shan , Xiaojuan Qi

Monocular visual odometry approaches that purely rely on geometric cues are prone to scale drift and require sufficient motion parallax in successive frames for motion estimation and 3D reconstruction. In this paper, we propose to leverage…

Computer Vision and Pattern Recognition · Computer Science 2018-07-26 Nan Yang , Rui Wang , Jörg Stückler , Daniel Cremers

Mobile robots rely on odometry to navigate through areas where localization fails. Visual odometry (VO) is a common solution for obtaining robust and consistent relative motion estimates of the vehicle frame. Contrarily, Global Positioning…

Robotics · Computer Science 2021-06-09 Benjamin Congram , Timothy D. Barfoot

Estimating motion from images is a well-studied problem in computer vision and robotics. Previous work has developed techniques to estimate the motion of a moving camera in a largely static environment (e.g., visual odometry) and to segment…

Robotics · Computer Science 2019-03-01 Kevin M. Judd , Jonathan D. Gammell , Paul Newman

Traditional monocular Visual-Inertial Odometry (VIO) systems struggle in low-texture environments where sparse visual features are insufficient for accurate pose estimation. To address this, dense Monocular Depth Estimation (MDE) has been…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Arda Alniak , Sinan Kalkan , Mustafa Mert Ankarali , Afsar Saranli , Abdullah Aydin Alatan

This paper proposes a self-supervised monocular image-to-depth prediction framework that is trained with an end-to-end photometric loss that handles not only 6-DOF camera motion but also 6-DOF moving object instances. Self-supervision is…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Houssem Boulahbal , Adrian Voicila , Andrew Comport

Visual localization and mapping is a crucial capability to address many challenges in mobile robotics. It constitutes a robust, accurate and cost-effective approach for local and global pose estimation within prior maps. Yet, in highly…

Computer Vision and Pattern Recognition · Computer Science 2018-07-11 Guoxiang Zhou , Berta Bescos , Marcin Dymczyk , Mark Pfeiffer , José Neira , Roland Siegwart

This paper proposes a novel approach to stereo visual odometry without stereo matching. It is particularly robust in scenes of repetitive high-frequency textures. Referred to as DSVO (Direct Stereo Visual Odometry), it operates directly on…

Computer Vision and Pattern Recognition · Computer Science 2019-09-17 Jiawei Mo , Junaed Sattar

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…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Reza Mahjourian , Martin Wicke , Anelia Angelova

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…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Huaizu Jiang , Erik Learned-Miller , Gustav Larsson , Michael Maire , Greg Shakhnarovich

Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and textureless scenarios. In this paper, we incorporate sparse but accurate depth measurements obtained from lidars…

Computer Vision and Pattern Recognition · Computer Science 2021-01-06 Bin Li , Mu Hu , Shuling Wang , Lianghao Wang , Xiaojin Gong

Most geometric approaches to monocular Visual Odometry (VO) provide robust pose estimates, but sparse or semi-dense depth estimates. Off late, deep methods have shown good performance in generating dense depths and VO from monocular images…

Robotics · Computer Science 2018-12-21 Vignesh Prasad , Brojeshwar Bhowmick

Curriculum Learning (CL), drawing inspiration from natural learning patterns observed in humans and animals, employs a systematic approach of gradually introducing increasingly complex training data during model development. Our work…

Robotics · Computer Science 2024-12-16 Assaf Lahiany , Oren Gal

We present a scalable self-supervised approach for segmenting feasible vehicle trajectories from monocular images for autonomous driving in complex urban environments. Leveraging large-scale dashcam videos, we treat recorded ego-vehicle…

Robotics · Computer Science 2026-03-25 Tomasz Frelek , Rohan Patil , Akshar Tumu , Henrik I. Christensen