Search Results for author: Yinlin Hu

Found 21 papers, 14 papers with code

Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

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.

6D Pose Estimation using RGB

NOPE: Novel Object Pose Estimation from a Single Image

1 code implementation23 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.

Object Pose Estimation

Rigidity-Aware Detection for 6D Object Pose Estimation

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.

6D Pose Estimation 6D Pose Estimation using RGB +3

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation

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.

6D Pose Estimation 6D Pose Estimation using RGB

Modular Quantization-Aware Training: Increasing Accuracy by Decreasing Precision in 6D Object Pose Estimation

no code implementations12 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.

6D Pose Estimation 6D Pose Estimation using RGB +1

LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation

no code implementations29 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.

6D Pose Estimation 6D Pose Estimation using RGB +4

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

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.

6D Pose Estimation 6D Pose Estimation using RGB +1

Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation

1 code implementation18 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.

6D Pose Estimation using RGB

Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects

no code implementations16 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.

Retrieval

Robust Differentiable SVD

2 code implementations8 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.

Image Classification Style Transfer

Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations

no code implementations19 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.

Pose Estimation

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

no code implementations15 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.

Denoising Pose Estimation

Single-Stage 6D Object Pose Estimation

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.

6D Pose Estimation 6D Pose Estimation using RGB +1

Segmentation-driven 6D Object Pose Estimation

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.

6D Pose Estimation 6D Pose Estimation using RGB +3

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

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.

3D Pose Estimation

Robust Interpolation of Correspondences for Large Displacement Optical Flow

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.

Optical Flow Estimation Superpixels

Efficient Coarse-To-Fine PatchMatch for Large Displacement Optical Flow

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.

Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.