中文
相关论文

相关论文: GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D P…

200 篇论文

We introduce Any6D, a model-free framework for 6D object pose estimation that requires only a single RGB-D anchor image to estimate both the 6D pose and size of unknown objects in novel scenes. Unlike existing methods that rely on textured…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Taeyeop Lee , Bowen Wen , Minjun Kang , Gyuree Kang , In So Kweon , Kuk-Jin Yoon

Estimating the 6D pose of unseen objects from monocular RGB images remains a challenging problem, especially due to the lack of prior object-specific knowledge. To tackle this issue, we propose RefPose, an innovative approach to object pose…

计算机视觉与模式识别 · 计算机科学 2025-05-19 Jaeguk Kim , Jaewoo Park , Keuntek Lee , Nam Ik Cho

On-board estimation of the pose of an uncooperative target spacecraft is an essential task for future on-orbit servicing and close-proximity formation flying missions. However, two issues hinder reliable on-board monocular vision based pose…

计算机视觉与模式识别 · 计算机科学 2018-09-20 Sumant Sharma , Connor Beierle , Simone D'Amico

Category-level object pose estimation aims to predict the 6D pose and 3D size of objects within given categories. Existing approaches for this task rely solely on 6D poses as supervisory signals without explicitly capturing the intrinsic…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Zhujun Li , Shuo Zhang , Ioannis Stamos

Humans are able to perform fast and accurate object pose estimation even under severe occlusion by exploiting learned object model priors from everyday life. However, most recently proposed pose estimation algorithms neglect to utilize the…

计算机视觉与模式识别 · 计算机科学 2019-12-23 Peiyu Yu , Yongming Rao , Jiwen Lu , Jie Zhou

Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through RANSAC-based algorithms or by directly regressing the pose with end-to-end…

计算机视觉与模式识别 · 计算机科学 2023-10-04 Jaime Corsetti , Davide Boscaini , Fabio Poiesi

Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…

计算机视觉与模式识别 · 计算机科学 2023-11-27 Pengyuan Wang , Takuya Ikeda , Robert Lee , Koichi Nishiwaki

We address the task of 6D pose estimation of known rigid objects from single input images in scenarios where the objects are partly occluded. Recent RGB-D-based methods are robust to moderate degrees of occlusion. For RGB inputs, no…

计算机视觉与模式识别 · 计算机科学 2018-06-19 Omid Hosseini Jafari , Siva Karthik Mustikovela , Karl Pertsch , Eric Brachmann , Carsten Rother

We introduce MegaPose, a method to estimate the 6D pose of novel objects, that is, objects unseen during training. At inference time, the method only assumes knowledge of (i) a region of interest displaying the object in the image and (ii)…

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning,…

计算机视觉与模式识别 · 计算机科学 2024-03-28 Bowen Wen , Wei Yang , Jan Kautz , Stan Birchfield

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This…

计算机视觉与模式识别 · 计算机科学 2020-03-24 Yinlin Hu , Pascal Fua , Wei Wang , Mathieu Salzmann

In this paper, we introduce neural texture learning for 6D object pose estimation from synthetic data and a few unlabelled real images. Our major contribution is a novel learning scheme which removes the drawbacks of previous works, namely…

计算机视觉与模式识别 · 计算机科学 2023-03-15 Hanzhi Chen , Fabian Manhardt , Nassir Navab , Benjamin Busam

We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to predict a translational and rotational update. At the core, we…

计算机视觉与模式识别 · 计算机科学 2018-10-09 Fabian Manhardt , Wadim Kehl , Nassir Navab , Federico Tombari

Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the core of GFPose is a time-dependent score network, which…

计算机视觉与模式识别 · 计算机科学 2022-12-19 Hai Ci , Mingdong Wu , Wentao Zhu , Xiaoxuan Ma , Hao Dong , Fangwei Zhong , Yizhou Wang

We propose a novel approach to jointly perform 3D shape retrieval and pose estimation from monocular images.In order to make the method robust to real-world image variations, e.g. complex textures and backgrounds, we learn an embedding…

计算机视觉与模式识别 · 计算机科学 2019-03-28 Kyaw Zaw Lin , Weipeng Xu , Qianru Sun , Christian Theobalt , Tat-Seng Chua

We present a novel approach to the detection and 3D pose estimation of objects in color images. Its main contribution is that it does not require any training phases nor data for new objects, while state-of-the-art methods typically require…

计算机视觉与模式识别 · 计算机科学 2019-09-02 Giorgia Pitteri , Slobodan Ilic , Vincent Lepetit

State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction…

计算机视觉与模式识别 · 计算机科学 2022-08-23 Stefan Thalhammer , Timothy Patten , Markus Vincze

Object pose estimation is frequently achieved by first segmenting an RGB image and then, given depth data, registering the corresponding point cloud segment against the object's 3D model. Despite the progress due to CNNs, semantic…

计算机视觉与模式识别 · 计算机科学 2018-05-17 Chaitanya Mitash , Abdeslam Boularias , Kostas Bekris

Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without CAD model knowledge. The idea is to leverage features learned…

计算机视觉与模式识别 · 计算机科学 2021-10-28 Yang Xiao , Yuming Du , Renaud Marlet

Solving Perspective-n-Point (PnP) problems is a traditional way of estimating object poses. Given outlier-contaminated data, a pose of an object is calculated with PnP algorithms of n = {3, 4} in the RANSAC-based scheme. However, the…

计算机视觉与模式识别 · 计算机科学 2021-06-11 Jeong-Kyun Lee , Young-Ki Baik , Hankyu Cho , Kang Kim , Duck Hoon Kim