English
Related papers

Related papers: Adaptive Continuous Visual Odometry from RGB-D Ima…

200 papers

A variational framework, initially developed for high-order mesh optimisation, is being extended for r-adaptation. The method is based on the minimisation of a functional of the mesh deformation. To achieve adaptation, elements of the…

Computational Geometry · Computer Science 2019-01-07 Julian Marcon , Michael Turner , David Moxey , Spencer J. Sherwin , Joaquim Peiró

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13].…

Computer Vision and Pattern Recognition · Computer Science 2015-02-17 Saurabh Gupta , Pablo Arbeláez , Ross Girshick , Jitendra Malik

This paper proposes a novel parameter selection strategy for kernel-based gradient descent (KGD) algorithms, integrating bias-variance analysis with the splitting method. We introduce the concept of empirical effective dimension to quantify…

Machine Learning · Statistics 2026-03-05 Xiaotong Liu , Yunwen Lei , Xiangyu Chang , Shao-Bo Lin

We consider the problem of 3D object pose estimation. While much recent work has focused on the RGB domain, the reliance on accurately annotated images limits their generalizability and scalability. On the other hand, the easily available…

Computer Vision and Pattern Recognition · Computer Science 2019-08-01 Georgios Georgakis , Srikrishna Karanam , Ziyan Wu , Jana Kosecka

Adaptive optimization methods are well known to achieve superior convergence relative to vanilla gradient methods. The traditional viewpoint in optimization, particularly in convex optimization, explains this improved performance by arguing…

Machine Learning · Computer Science 2022-11-07 Kaiqi Jiang , Dhruv Malik , Yuanzhi Li

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object…

Computer Vision and Pattern Recognition · Computer Science 2015-08-19 Andreas Eitel , Jost Tobias Springenberg , Luciano Spinello , Martin Riedmiller , Wolfram Burgard

Scale ambiguity is a fundamental problem in monocular visual odometry. Typical solutions include loop closure detection and environment information mining. For applications like self-driving cars, loop closure is not always available, hence…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Rui Tian , Yunzhou Zhang , Delong Zhu , Shiwen Liang , Sonya Coleman , Dermot Kerr

Detection of moving objects is an essential capability in dealing with dynamic environments. Most moving object detection algorithms have been designed for color images without depth. For robotic navigation where real-time RGB-D data is…

Computer Vision and Pattern Recognition · Computer Science 2020-09-21 Haram Kim , Pyojin Kim , H. Jin Kim

In this paper, we focus on the question: how might mobile robots take advantage of affordable RGB-D sensors for object detection? Although current CNN-based object detectors have achieved impressive results, there are three main drawbacks…

Robotics · Computer Science 2021-04-27 Jianxiong Cai , Jiawei Hou , Yiren Lu , Hongyu Chen , Laurent Kneip , Sören Schwertfeger

Monocular visual odometry (VO) has attracted extensive research attention by providing real-time vehicle motion from cost-effective camera images. However, state-of-the-art optimization-based monocular VO methods suffer from the scale…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Sen Zhang , Jing Zhang , Dacheng Tao

Deep learning using Convolutional Neural Networks (CNNs) has been shown to significantly out-performed many conventional vision algorithms. Despite efforts to increase the CNN efficiency both algorithmically and with specialized hardware,…

Computer Vision and Pattern Recognition · Computer Science 2021-05-24 Carlos Mauricio Villegas Burgos , Tianqi Yang , Nick Vamivakas , Yuhao Zhu

Deep networks have brought significant advances in robot perception, enabling to improve the capabilities of robots in several visual tasks, ranging from object detection and recognition to pose estimation, semantic scene segmentation and…

Robotics · Computer Science 2019-04-03 Fabio Cermelli , Massimiliano Mancini , Elisa Ricci , Barbara Caputo

While the BD-rate performance of recent learned video codec models in both low-delay and random-access modes exceed that of respective modes of traditional codecs on average over common benchmarks, the performance improvements for…

Image and Video Processing · Electrical Eng. & Systems 2025-10-13 Ahmet Bilican , M. Akın Yılmaz , A. Murat Tekalp

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…

Computer Vision and Pattern Recognition · Computer Science 2020-02-10 Yihan Du , Yan Yan , Si Chen , Yang Hua

In point-based sensing systems such as coordinate measuring machines (CMM) and laser ultrasonics where complete sensing is impractical due to the high sensing time and cost, adaptive sensing through a systematic exploration is vital for…

Machine Learning · Statistics 2019-10-08 Hao Yan , Kamran Paynabar , Jianjun Shi

Due to inevitable noises introduced during scanning and quantization, 3D reconstruction via RGB-D sensors suffers from errors both in geometry and texture, leading to artifacts such as camera drifting, mesh distortion, texture ghosting, and…

Computer Vision and Pattern Recognition · Computer Science 2022-09-13 Jingbo Zhang , Ziyu Wan , Jing Liao

In this paper we study the problem of object detection for RGB-D images using semantically rich image and depth features. We propose a new geocentric embedding for depth images that encodes height above ground and angle with gravity for…

Computer Vision and Pattern Recognition · Computer Science 2014-07-23 Saurabh Gupta , Ross Girshick , Pablo Arbeláez , Jitendra Malik

In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Nuo Xu , Chunlei Huo , Jiacheng Guo , Yiwei Liu , Jian Wang , Chunhong Pan

Most visual odometry algorithm for a monocular camera focuses on points, either by feature matching, or direct alignment of pixel intensity, while ignoring a common but important geometry entity: edges. In this paper, we propose an odometry…

Computer Vision and Pattern Recognition · Computer Science 2017-03-21 Shichao Yang , Sebastian Scherer

Autonomous robots often rely on monocular cameras for odometry estimation and navigation. However, the scale ambiguity problem presents a critical barrier to effective monocular visual odometry. In this paper, we present CodedVO, a novel…

Robotics · Computer Science 2024-07-26 Sachin Shah , Naitri Rajyaguru , Chahat Deep Singh , Christopher Metzler , Yiannis Aloimonos