☆ 4.5 Article

3D Object Tracking for Rough Models

COMPUTER GRAPHICS FORUM (2023)

Related references

Note: Only part of the references are listed.
Proceedings Paper Computer Science, Artificial Intelligence

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Bowen Wen et al.

Summary: A method for real-time tracking and 3D reconstruction of unknown objects is proposed, which works for arbitrary objects even in the absence of visual texture, and can handle various challenging situations.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR (2023)

Add to Collection
Article Computer Science, Artificial Intelligence

SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World

Manuel Stoiber et al.

Summary: This paper presents a region-based sparse method for tracking the 3D position of texture-less objects in cluttered scenes. By considering the sparse distribution of image information and global/local uncertainties, this method achieves high computational efficiency and tracking quality.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2022)

Add to Collection
Article Computer Science, Software Engineering

Pixel-Wise Weighted Region-Based 3D Object Tracking Using Contour Constraints

Hong Huang et al.

Summary: This study proposes a novel region-based method to address the challenges of partial occlusions and ambiguous colors in monocular 3D object tracking. The approach utilizes contour constraints to derive a pixel-wise weighted region-based cost function. Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches, especially in complex scenarios.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2022)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation

Yilin Wen et al.

Summary: This paper presents a scalable 6D pose estimation method for rigid objects from RGB images. By using an auto-encoding framework and contrastive metric learning, the method can handle multiple objects and generalize to novel objects. Experimental results on two benchmarks show state-of-the-art performance, and improved scalability is demonstrated in a more challenging setting.

COMPUTER VISION, ECCV 2022, PT IX (2022)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

Large-Displacement 3D Object Tracking with Hybrid Non-local Optimization

Xuhui Tian et al.

Summary: In this paper, a fast and effective non-local 3D tracking method is proposed, which can adapt to different frame displacements and outperform previous methods in terms of accuracy and real-time performance.

COMPUTER VISION, ECCV 2022, PT XXII (2022)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

Yuan Liu et al.

Summary: This paper presents Gen6D, a generalizable model-free 6-DoF object pose estimator. Unlike existing methods, Gen6D does not require high-quality object models, depth maps, or object masks during testing. Experimental results demonstrate that Gen6D achieves state-of-the-art performance on model-free datasets and competitive results on the LINEMOD dataset compared to instance-specific pose estimators.

COMPUTER VISION - ECCV 2022, PT XXXII (2022)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

OnePose: One-Shot Object Pose Estimation without CAD Models

Jiaming Sun et al.

Summary: OnePose is a novel method for object pose estimation that does not rely on CAD models and can handle objects in arbitrary categories. It efficiently matches 2D interest points in query images with 3D points in the SfM model, enabling stable detection and tracking of 6D poses in real-time.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

Van Nguyen Nguyen et al.

Summary: This study presents a method that can recognize new objects and estimate their 3D pose in RGB images even under partial occlusions. The method does not require a training phase on real images, only CAD models of the objects. It utilizes local object representations and template matching to achieve generalization to new objects without retraining.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

FS6D: Few-Shot 6D Pose Estimation of Novel Objects

Yisheng He et al.

Summary: This work addresses the problem of estimating the 6D pose of unknown objects using a few support views and emphasizes the importance of exploring appearance and geometric relationships. A large-scale dataset for network pre-training is proposed, along with an online texture blending approach to enrich appearance diversity.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection
Article Computer Science, Software Engineering

Fast 3D texture-less object tracking with geometric contour and local region

Jiachen Li et al.

Summary: This paper proposes a fast 3D object tracking framework that reduces the reprojection process to one time to improve calculation efficiency while maintaining optimization accuracy. By utilizing the object's geometric properties and refining pose in a local region, the proposed method achieves nearly doubled efficiency and stable tracking performance on mobile phones with a faster version.

COMPUTERS & GRAPHICS-UK (2021)

Add to Collection
Article Computer Science, Hardware & Architecture

3D Object Tracking with Adaptively Weighted Local Bundles

Jia-Chen Li et al.

Summary: The paper introduces a new 3D object tracking method, AWLB tracker, to handle more complicated cases by adaptively weighted local bundles. The proposed method improves the accuracy of object tracking by adaptively weighting local bundles.

JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY (2021)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

Yijia Weng et al.

Summary: In this paper, we introduce a unified framework for category-level online pose tracking of objects from point cloud sequences. The proposed framework is capable of handling pose tracking for both rigid object instances and articulated objects through a novel end-to-end pipeline, achieving state-of-the-art performance on benchmark datasets.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection
Proceedings Paper Automation & Control Systems

BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

Bowen Wen et al.

Summary: BundleTrack is a general framework for tracking the 6D pose of novel objects, utilizing deep learning and memory-augmented pose graph optimization for long-term, low-drift tracking without relying on 3D models. It achieves real-time performance with comparable results to methods that require object instance CAD models.

2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2021)

Add to Collection
Article Computer Science, Software Engineering

An Occlusion-aware Edge-Based Method for Monocular 3D Object Tracking using Edge Confidence

Hong Huang et al.

COMPUTER GRAPHICS FORUM (2020)

Add to Collection
Article Computer Science, Artificial Intelligence

Occlusion-Aware Region-Based 3D Pose Tracking of Objects With Temporally Consistent Polar-Based Local Partitioning

Leisheng Zhong et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

Add to Collection
Article Computer Science, Artificial Intelligence

A Robust Monocular 3D Object Tracking Method Combining Statistical and Photometric Constraints

Leisheng Zhong et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2019)

Add to Collection
Article Computer Science, Artificial Intelligence

A Region-Based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking

Henning Tjaden et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection
Article Computer Science, Information Systems

Robust edge-based 3D object tracking with direction-based pose validation

Bin Wang et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2019)

Add to Collection
Article Computer Science, Artificial Intelligence

Robust 3D Object Tracking from Monocular Images Using Stable Parts

Alberto Crivellaro et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

Real-Time Monocular Pose Estimation of 3D Objects using Temporally Consistent Local Color Histograms

Henning Tjaden et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection
Article Computer Science, Artificial Intelligence

2D-3D Pose Estimation of Heterogeneous Objects Using a Region Based Approach

Jonathan Hexner et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2016)

Add to Collection
Article Computer Science, Software Engineering

Pose Estimation for Augmented Reality: A Hands-On Survey

Eric Marchand et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2016)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects

Henning Tjaden et al.

COMPUTER VISION - ECCV 2016, PT IV (2016)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

A Direct Method for Robust Model-Based 3D Object Tracking from a Monocular RGB Image

Byung-Kuk Seo et al.

COMPUTER VISION - ECCV 2016 WORKSHOPS, PT III (2016)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

D2CO: Fast and Robust Registration of 3D Textureless Objects Using the Directional Chamfer Distance

Marco Imperoli et al.

COMPUTER VISION SYSTEMS (ICVS 2015) (2015)

Add to Collection
Article Computer Science, Software Engineering

Optimal Local Searching for Fast and Robust Textureless 3D Object Tracking in Highly Cluttered Backgrounds

Byung-Kuk Seo et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2014)

Add to Collection
Proceedings Paper Computer Science, Artificial Intelligence

Robust 3D Tracking with Descriptor Fields

Alberto Crivellaro et al.

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2014)

Add to Collection
Article Computer Science, Artificial Intelligence

PWP3D: Real-Time Segmentation and Tracking of 3D Objects

Victor A. Prisacariu et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2012)

Add to Collection
Article Computer Science, Artificial Intelligence

Real-time visual tracking of complex structures

T Drummond et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2002)

Add to Collection
Webinars Posters Questions Hubs Funding Journals Papers Connect Collections Reviewers About Us FAQs Mobile App Privacy Policy Terms of Use
© Peeref 2019-2024. All rights reserved.