1 code implementation • ICCV 2023 • Yang Hai, Rui Song, Jiaojiao Li, David Ferstl, Yinlin Hu
Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range.
1 code implementation • CVPR 2023 • Yang Hai, Rui Song, Jiaojiao Li, Yinlin Hu
In this work, we propose a shape-constraint recurrent matching framework for 6D object pose estimation.
1 code implementation • 23 Mar 2023 • Van Nguyen Nguyen, Thibault Groueix, Yinlin Hu, Mathieu Salzmann, Vincent Lepetit
The practicality of 3D object pose estimation remains limited for many applications due to the need for prior knowledge of a 3D model and a training period for new objects.
2 code implementations • CVPR 2023 • Yang Hai, Rui Song, Jiaojiao Li, Mathieu Salzmann, Yinlin Hu
To address this, we propose a rigidity-aware detection method exploiting the fact that, in 6D pose estimation, the target objects are rigid.
1 code implementation • ICCV 2023 • Fulin Liu, Yinlin Hu, Mathieu Salzmann
Here, we argue that this conflicts with the averaging nature of the PnP problem, leading to gradients that may encourage the network to degrade the accuracy of individual correspondences.
no code implementations • 12 Mar 2023 • Saqib Javed, Chengkun Li, Andrew Price, Yinlin Hu, Mathieu Salzmann
Edge applications, such as collaborative robotics and spacecraft rendezvous, demand efficient 6D object pose estimation on resource-constrained embedded platforms.
no code implementations • 29 Nov 2022 • Chen Zhao, Yinlin Hu, Mathieu Salzmann
The prior can be used to initialize the 3D object translation and facilitate 3D object rotation estimation.
no code implementations • CVPR 2023 • Shuxuan Guo, Yinlin Hu, Jose M. Alvarez, Mathieu Salzmann
Knowledge distillation facilitates the training of a compact student network by using a deep teacher one.
2 code implementations • CVPR 2022 • Van Nguyen Nguyen, Yinlin Hu, Yang Xiao, Mathieu Salzmann, Vincent Lepetit
It relies on a small set of training objects to learn local object representations, which allow us to locally match the input image to a set of "templates", rendered images of the CAD models for the new objects.
1 code implementation • 18 Mar 2022 • Yinlin Hu, Pascal Fua, Mathieu Salzmann
Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction.
no code implementations • 16 Mar 2022 • Chen Zhao, Yinlin Hu, Mathieu Salzmann
In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images.
2 code implementations • 8 Apr 2021 • Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann
Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.
2 code implementations • CVPR 2021 • Yinlin Hu, Sebastien Speierer, Wenzel Jakob, Pascal Fua, Mathieu Salzmann
6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting.
no code implementations • 19 Aug 2020 • Zhigang Li, Yinlin Hu, Mathieu Salzmann, Xiangyang Ji
We achieve state of the art performance on LINEMOD, and OccludedLINEMOD in without real-pose setting, even outperforming methods that rely on real annotations during training on Occluded-LINEMOD.
no code implementations • 15 Apr 2020 • Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann
In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.
1 code implementation • CVPR 2020 • Yinlin Hu, Pascal Fua, Wei Wang, Mathieu Salzmann
Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task.
2 code implementations • NeurIPS 2019 • Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann
Eigendecomposition (ED) is widely used in deep networks.
5 code implementations • CVPR 2019 • Yinlin Hu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann
The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm.
Ranked #4 on 6D Pose Estimation using RGB on YCB-Video
no code implementations • ECCV 2018 • Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system.
1 code implementation • CVPR 2017 • Yinlin Hu, Yunsong Li, Rui Song
In this paper, we present a Robust Interpolation method of Correspondences (called RicFlow) to overcome the weakness.
1 code implementation • CVPR 2016 • Yinlin Hu, Rui Song, Yunsong Li
Inspired by the nearest neighbor field (NNF) algorithms, our approach, called CPM (Coarse-to-fine PatchMatch), blends an efficient random search strategy with the coarse-to-fine scheme for optical flow problem.