Submission: Coupled Iterative Refinement/HB

Download submission
Submission name
Submission time (UTC) April 24, 2022, 11:08 p.m.
User lahav
Task 6D localization of seen objects
Dataset HB
Training model type Default
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description Single view. Dataset splits: train_pbr
Evaluation scores

Method: Coupled Iterative Refinement

User lahav
Publication Coupled Iterative Refinement for 6D Multi-Object Pose Estimation, CVPR 2022
Training image modalities RGB-D
Test image modalities RGB-D

We propose a new approach to 6D object pose estimation which consists of an end-to-end differentiable architecture that makes use of geometric knowledge. Our approach it- eratively refines both pose and correspondence in a tightly coupled manner, allowing us to dynamically remove outliers to improve accuracy. We use a novel differentiable layer to perform pose refinement by solving an optimization problem we refer to as Bidirectional Depth-Augmented Perspective- N-Point (BD-PnP).

Computer specifications 2 RTX-3090s