Method: MRC-Net

User ymao
Publication Yuelong Li*, Yafei Mao*, Raja Bala, Sunil Hadap: MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation, CVPR 2024.
Implementation https://github.com/amzn/mrc-net-6d-pose
Training image modalities RGB
Test image modalities RGB
Description

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation, CVPR 2024, https://arxiv.org/abs/2403.08019, MRC-Net is a simple correspondence-free RGB-only 6DoF pose estimation model with leading accuracy and near real-time speed! It reformulates the conventional multitask classification+regression approach into a new sequential design. The two-sequential stages are bridged by a novel multi-scale correlation structure.

Computer specifications Nvidia V100

Public submissions

Date Submission name Dataset
2024-03-18 20:48 PBRReal(DefaultDetections2022) T-LESS
2024-03-18 20:48 PBR(DefaultDetections2022) T-LESS
2024-03-18 20:49 PBR(DefaultDetections2022) LM-O
2024-03-18 20:49 PBR(DefaultDetections2022) YCB-V
2024-03-18 20:50 PBR(DefaultDetections2022) ITODD
2024-03-21 18:51 PBRReal(DefaultDetections2022) YCB-V