paper-with-me

Papers

HybridPose: 6D Object Pose Estimation under Hybrid Representations

2020-01-07 · CVPR 2020 6 · Chen Song, Jiaru Song, Qi-Xing Huang

We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). Different intermediate representations used by HybridPose can all be predicted by the same simple neural network, and outliers in predicted intermediate representations are filtered by a robust regression module. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and accuracy. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 47.5%, representing a state-of-the-art performance. The implementation of HybridPose is available at https://github.com/chensong1995/HybridPose.

📄 PDF Abstract BibTeX arXiv:2001.01869

Code (3)

chensong1995/HybridPose 공식 구현 pytorch
chronoshell/copyydscsv pytorch
hz-ants/HybridPose pytorch

Tasks

6D Pose Estimation using RGBObjectPose Estimationregression

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Hybrid model for Single-Stage Multi-Person Pose Estimation

2023-05-02 · Jonghyun Kim, Bosang Kim, Hyotae Lee, Jungpyo Kim 외

In general, human pose estimation methods are categorized into two approaches according to their architectures: regression (i.e., heatmap-free) and heatmap-based methods. The former one directly estimates precise coordin…

Multi-Person Pose EstimationPose EstimationQuantizationregression

A Theory-grounded Hybrid Neural Network Integrating Complementary Estimation Mechanisms for Stable Visual Object TrackingA

2026-06-21 · Yancheng Zhou, Hanle Zheng, Lei Deng, Yujie Wu arxiv

Hybrid neural networks (HNNs) that integrate artificial neural networks (ANNs) with brain-inspired neural networks have achieved broad success across perception and control tasks. However, much of the current success is …

Visual Object TrackingVisual Tracking

THE-Pose: Topological Prior with Hybrid Graph Fusion for Estimating Category-Level 6D Object Pose

2025-12-11 · Eunho Lee, Chaehyeon Song, Seunghoon Jeong, Ayoung Kim arxiv

Category-level object pose estimation requires both global context and local structure to ensure robustness against intra-class variations. However, 3D graph convolution (3D-GC) methods only focus on local geometry and d…

6D Pose Estimation

A Hybrid Objective Function for Robustness of Artificial Neural Networks -- Estimation of Parameters in a Mechanical System

2020-04-16 · Jan Sokolowski, Volker Schulz, Udo Schröder, Hans-Peter Beise

In several studies, hybrid neural networks have proven to be more robust against noisy input data compared to plain data driven neural networks. We consider the task of estimating parameters of a mechanical vehicle model…

Advanced Object Detection and Pose Estimation with Hybrid Task Cascade and High-Resolution Networks

2025-02-06 · Yuhui Jin, YaQiong Zhang, Zheyuan Xu, Wenqing Zhang 외

In the field of computer vision, 6D object detection and pose estimation are critical for applications such as robotics, augmented reality, and autonomous driving. Traditional methods often struggle with achieving high a…

Autonomous DrivingObjectobject-detectionObject Detection+1