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

Public submissions

Date Submission name Dataset
2022-04-24 19:36 - TUD-L
2022-04-24 19:57 - IC-BIN
2022-04-24 20:35 - T-LESS
2022-04-24 21:58 - YCB-V
2022-04-24 22:03 - LM-O
2022-04-24 23:08 - HB
2022-04-25 18:52 - ITODD